% Encoding: UTF-8
@inproceedings{Abreu:2007,
  title        = {An Evaluation of Similarity Coefficients for Software Fault Localization},
  author       = {Abreu, Rui and Zoeteweij, Peter and {van Gemund}, {Arjan J. C.}},
  year         = 2007,
  journal      = {IEEE Xplore},
  booktitle    = {2006 12th Pacific Rim International Symposium on Dependable Computing (PRDC'06)},
  doi          = {10.1109/PRDC.2006.18}
}
@misc{Adams:2017,
  title        = {Ruby port of UEALite Stemmer},
  author       = {Adams, Jason},
  year         = 2017,
  url          = {https://github.com/ealdent/uea-stemmer}
}
@article{Ainsworth:1973,
  title        = {A System for Converting Text into Speech},
  author       = {Ainsworth, {William A.}},
  year         = 1973,
  month        = jun,
  journal      = {IEEE Transactions on Audio and Electroacoustics},
  volume       = {AU-21},
  number       = 3,
  pages        = {288--290},
  doi          = {10.1109/TAU.1973.1162452}
}
@article{Amon:2012,
  title        = {Algoritmo fon{\'{e}}tico para detecci{\'{o}}n de cadenas de texto duplicadas en el idioma espa{\~{n}}ol},
  author       = {Am{\'{o}}n, Iv{\'{a}}n and Moreno, Francisco and Echeverri, Jaime},
  year         = 2012,
  month        = jun,
  journal      = {Revista Ingenier\'{\i}as Universidad de Medell\'{\i}n},
  volume       = 11,
  number       = 20,
  pages        = {127--138},
  issn         = {1692-3324},
  url          = {http://www.scielo.org.co/scielo.php?pid=S1692-33242012000100011\&script=sci\_abstract\&tlng=es}
}
@book{Anderberg:1973,
  title        = {Cluster Analysis for Applications},
  author       = {Anderberg, {Michael R.}},
  year         = 1973,
  publisher    = {Academic Press},
  address      = {New York},
  doi          = {10.1016/C2013-0-06161-0}
}
@article{Anderson:2004,
  title        = {Spatial variation and effects of habitat on temperate reef fish assemblages in northeastern New Zealand},
  author       = {Anderson, {Marti J.} and Millar, {Russell B.}},
  year         = 2004,
  journal      = {Journal of Experimental Marine Biology and Ecology},
  volume       = 305,
  pages        = {191--221},
  doi          = {10.1016/j.jembe.2003.12.011}
}
@article{Andres:2004,
  title        = {Delta: a new measure of agreement between two raters},
  author       = {Andr{\'{e}}s, {A. Mart{\'{i}}n} and Marzo, {P. Femia}},
  year         = 2004,
  month        = may,
  journal      = {British Journal of Mathematical and Statistical Psychology},
  volume       = 57,
  number       = 1,
  pages        = {1--20},
  doi          = {10.1348/000711004849268}
}
@article{Austin:1977,
  title        = {Evaluation of Some Coefficients for Use in Numerical Taxonomy of Microorganisms},
  author       = {Austin, Brian and Colwell, {Rita R.}},
  year         = 1977,
  month        = jul,
  journal      = {International Journal of Systematic Bacteriology},
  volume       = 27,
  number       = 3,
  pages        = {204--210},
  doi          = {10.1099/00207713-27-3-204}
}
@techreport{Axelsson:2009,
  title        = {SfinxBis},
  author       = {Axelsson, P{\aa}l},
  year         = 2009,
  month        = apr,
  url          = {http://www.swami.se/download/18.248ad5af12aa8136533800091/SfinxBis.pdf},
  institution  = {Swedish Alliance for Middleware Infrastructure}
}
@article{BaroniUrbani:1976,
  title        = {Similarity of Binary Data},
  author       = {Baroni-Urbani, Cesare and Buser, {Mauro W.}},
  year         = 1976,
  month        = sep,
  journal      = {Systematic Biology},
  volume       = 25,
  number       = 3,
  pages        = {251--259},
  doi          = {10.2307/2412493}
}
@inproceedings{Bartolini:2002,
  title        = {String Matching with Metric Trees Using an Approximate Distance},
  author       = {Bartolini, Ilaria and Ciaccia, Paolo and Patella, Marco},
  year         = 2002,
  booktitle    = {SPIRE 2002: String Processing and Information Retrieval},
  publisher    = {Springer Berlin Heidelberg},
  address      = {Berlin, Heidelberg},
  pages        = {271--283},
  doi          = {10.1007/3-540-45735-6\_24},
  isbn         = {978-3-540-45735-0},
  url          = {http://www-db.disi.unibo.it/research/papers/SPIRE02.pdf},
  editor       = {Laender, {Alberto H. F.} and Oliveira, {Arlindo L.}}
}
@article{Batagelj:1995,
  title        = {Comparing Resemblance Measures},
  author       = {Batagelj, Vladimir and Bren, Matev\v{z}},
  year         = 1995,
  month        = mar,
  journal      = {Journal of Classification},
  volume       = 12,
  number       = 1,
  pages        = {73--90},
  doi          = {10.1007/BF01202268}
}
@article{Baulieu:1989,
  title        = {A Classification of Presence/Absence Based Dissimilarity Coefficients},
  author       = {Baulieu, {Forrest B.}},
  year         = 1989,
  journal      = {Journal of Classification},
  volume       = 6,
  number       = 1,
  pages        = {233--246},
  doi          = {10.1007/BF01908601}
}
@article{Baulieu:1997,
  title        = {Two Variant Axiom Systems for Presence/Absence Based Dissimilarity Coefficients},
  author       = {Baulieu, {Forrest B.}},
  year         = 1997,
  journal      = {Journal of Classification},
  volume       = 14,
  number       = 1,
  pages        = {159--170},
  doi          = {10.1007/s003579900009}
}
@article{Beider:2008,
  title        = {Beider-Morse Phonetic Matching: An Alternative to Soundex with Fewer False Hits},
  author       = {Beider, Alexander and Morse, {Stephen P.}},
  year         = 2008,
  month        = {Summer},
  journal      = {International Review of Jewish Genealogy},
  number       = 1,
  url          = {https://stevemorse.org/phonetics/bmpm.htm}
}
@book{Benini:1901,
  title        = {Principii di Demografia},
  author       = {Benini, Rudolfo},
  year         = 1901,
  publisher    = {G. Barbera},
  address      = {Firenze},
  series       = {Manuali Barbera di Scienze Giuridiche Sociali e Politiche},
  number       = 29,
  url          = {http://www.archive.org/stream/principiididemo00benigoog}
}
@article{Bennet:1954,
  title        = {Communications Through Limited-Response Questioning},
  author       = {Bennet, {E. M.} and Alpert, {R.} and Goldstein, {A. C.}},
  year         = 1954,
  journal      = {Public Opinion Quarterly},
  volume       = 18,
  number       = 3,
  pages        = {303--308},
  doi          = {10.1086/266520}
}
@article{Bhattacharyya:1946,
  title        = {On a Measure of Divergence between Two Multinomial Populations},
  author       = {Bhattacharyya, {Anil Kumar}},
  year         = 1946,
  month        = jul,
  journal      = {Sankhy\={a}: The Indian Journal of Statistics (1933-1960)},
  volume       = 7,
  number       = 4,
  pages        = {401--406},
  doi          = {10.2307/25047882}
}
@article{Bouchard:1980,
  title        = {Name Variations and Computerized Record Linkage},
  author       = {Bouchard, Gerard and Pouyez, Christian},
  year         = 1980,
  journal      = {Historical Methods: A Journal of Quantitative and Interdisciplinary History},
  volume       = 13,
  number       = 2,
  pages        = {119--125},
  doi          = {10.1080/01615440.1980.10594037}
}
@article{Bouchard:1981,
  title        = {FONEM: Un code de transcription phon{\'{e}}tique pour la reconstitution automatique des familles saguenayennes},
  author       = {Bouchard, G{\'{e}}rard and Brard, Patrick and Lavoie, Yolande},
  year         = 1981,
  journal      = {Population},
  volume       = 36,
  number       = 6,
  doi          = {10.2307/1532326},
  url          = {http://www.persee.fr/doc/pop\_0032-4663\_1981\_num\_36\_6\_17248}
}
@misc{Boyce:1998,
  title        = {Information on the Refined Soundex Algorithm},
  author       = {Boyce, {Carolyn B.}},
  year         = 1998,
  month        = nov,
  url          = {https://web.archive.org/web/20010513121003/http://www.bluepoof.com:80/Soundex/info2.html}
}
@article{Boytsov:2011,
  title        = {Indexing Methods for Approximate Dictionary Searching: Comparative Analysis},
  author       = {Boytsov, Leonid},
  year         = 2011,
  month        = may,
  journal      = {Journal of Experimental Algorithmics},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 16,
  pages        = {1.1:1.1--1.1:1.91},
  doi          = {10.1145/1963190.1963191},
  issn         = {1084-6654},
  acmid        = 1963191,
  articleno    = {1.1},
  issue_date   = 2011,
  keywords     = {k-errata tree, q-gram, q-sample, Damerau-Levenshtein distance, Levenshtein distance, NR-grep, agrep, approximate searching, frequency distance, frequency vector trie, metric trees, neighborhood generation, trie},
  numpages     = {1.81}
}
@article{Brainerd:1951,
  title        = {The Place of Chronological Ordering in Archaeological Analysis},
  author       = {Brainerd, {George W.}},
  year         = 1951,
  month        = apr,
  journal      = {American Antiquity},
  volume       = 16,
  number       = 4,
  pages        = {301--313},
  doi          = {10.2307/276979}
}
@book{BraunBlanquet:1932,
  title        = {Plant Sociology: The Study of Plant Communities},
  author       = {Braun-Blanquet, Josias},
  year         = 1932,
  publisher    = {McGraw-Hill Book Company},
  address      = {New York},
  url          = {https://archive.org/details/plantsociologyst00brau}
}
@article{Bray:1957,
  title        = {An ordination of upland forest communities of southern Wisconsin},
  author       = {Bray, {J. Roger} and Curtis, {John T.}},
  year         = 1957,
  month        = feb,
  journal      = {Ecological Monographs},
  volume       = 27,
  number       = 4,
  pages        = {325--349},
  doi          = {10.2307/1942268},
  url          = {http://cescos.fau.edu/gawliklab/papers/BrayJRandJTCurtis1957.pdf}
}
@inproceedings{Broder:1997,
  title        = {On the resemblance and containment of documents},
  author       = {Broder, {Andrei Z.}},
  year         = 1997,
  booktitle    = {Compression and Complexity of Sequences: Proceedings, Positano, Amalfitan Coast, Salerno, Italy, June 11-13, 1997},
  pages        = {21--29},
  doi          = {10.1109/SEQUEN.1997.666900}
}
@techreport{Burrows:1994,
  title        = {A block sorting lossless data compression algorithm},
  author       = {Burrows, Michael and Wheeler, {David J.}},
  year         = 1994,
  month        = may,
  address      = {Palo Alto},
  number       = 124,
  url          = {http://www.hpl.hp.com/techreports/Compaq-DEC/SRC-RR-124.html},
  institution  = {Digital Equipment Corporation},
  type         = {SRC Research Report}
}
@article{Cao:1997,
  title        = {Similarity measure bias in river benthic aufwuchs community analysis},
  author       = {Cao, Yong and Bark, {Anthony W.} and Williams, {W. Peter}},
  year         = 1997,
  journal      = {Water Environment Research},
  volume       = 69,
  number       = 1,
  pages        = {95--106},
  doi          = {10.2175/106143097x125227}
}
@techreport{Caumanns:1999,
  title        = {A Fast and Simple Stemming Algorithm for German Words},
  author       = {Caumanns, J{\"{o}}rg},
  year         = 1999,
  url          = {https://refubium.fu-berlin.de/bitstream/handle/fub188/18405/tr-b-99-16.pdf},
  institution  = {Free University of Berlin}
}
@article{Cha:2006,
  title        = {Enhancing Binary Feature Vector Similarity Measures},
  author       = {Cha, {Sung-Hyuk} and Tappert, {Charles C.} and Yoon, Sungsoo},
  year         = 2006,
  journal      = {Journal of Pattern Recognition Research},
  volume       = 1,
  number       = 1,
  pages        = {63--77},
  doi          = {10.13176/11.20}
}
@inproceedings{Cha:2008,
  title        = {Taxonomy of Nominal Type Histogram Distance Measures},
  author       = {Cha, Sung-Hyuk},
  year         = 2008,
  booktitle    = {Proceedings of the American Conference on Applied Mathematics (MATH '08)},
  url          = {http://www.wseas.us/e-library/conferences/2008/harvard/math/49-577-887.pdf}
}
@article{Chao:2004,
  title        = {A new statistical approach for assessing similarity of species composition with incidence and abundance data},
  author       = {Chao, Anne and Chazdon, {Robin L.} and Colwell, {Robert K.} and Shen, {Tsung-Jen}},
  year         = 2004,
  journal      = {Ecology Letters},
  volume       = 8,
  number       = 2,
  pages        = {148--159},
  doi          = {10.1111/j.1461-0248.2004.00707.x}
}
@article{Choi:2010,
  title        = {A Survey of Binary Similarity and Distance Measures},
  author       = {Choi, Seung-Seok and Cha, Sung-Hyuk and Tappert, {Charles C.}},
  year         = 2010,
  journal      = {Systemics, Cybernetics and Informatics},
  volume       = 8,
  number       = 1,
  pages        = {43--48}
}
@techreport{Christen:2006,
  title        = {A Comparison of Personal Name Matching: Techniques and Practical Issues},
  author       = {Christen, Peter},
  year         = 2006,
  address      = {Canberra, Australia},
  number       = {TR-CS-06-02},
  url          = {https://openresearch-repository.anu.edu.au/bitstream/1885/44521/3/TR-CS-06-02.pdf},
  institution  = {Australian National University}
}
@misc{Christen:2011,
  title        = {Febrl (Freely extensible biomedical record linkage) -- encode.py},
  author       = {Christen, Peter},
  year         = 2011,
  month        = dec,
  url          = {https://sourceforge.net/projects/febrl/}
}
@incollection{Church:1991,
  title        = {Using statistics in lexical analysis},
  author       = {Church, Kenneth and Gale, William and Hanks, Patrick and Hindle, Donald},
  year         = 1991,
  booktitle    = {Lexical Acquisition: Exploiting On-Line Resources to Build up a Lexicon},
  publisher    = {Lawrence Erlbaum},
  address      = {Hillsdale, NJ},
  pages        = {115--164}
}
@misc{Churchill:2005,
  title        = {UEAstem.java},
  author       = {Churchill, Richard},
  url          = {http://lemur.cmp.uea.ac.uk/Research/stemmer/UEAstem.java}
}
@article{Cilibrasi:2005,
  title        = {Clustering by compression},
  author       = {Cilibrasi, Rudi and Vitanyi, {Paul Michael B{\'{e}}la}},
  year         = 2005,
  month        = apr,
  journal      = {IEEE Transactions on Information Theory},
  volume       = 51,
  number       = 4,
  pages        = {1523--1545},
  doi          = {10.1109/TIT.2005.844059},
  issn         = {0018-9448},
  url          = {https://ieeexplore.ieee.org/document/1412045},
  keywords     = {genetics;data compression;data analysis;cellular biophysics;data mining;pattern clustering;hierarchical unsupervised clustering;NCD;normalized compression distance;compressed data files;Kolmogorov complexity;distance matrix;dendrogram;quartet method;public software;mammalian evolution;mitochondrial genomic analysis;Eutherian order;Marsupionta hypothesis;Theria hypothesis;heterogenous data analysis;parameter-free data mining;quartet tree method;universal dissimilarity distance;Genomics;Bioinformatics;Robustness;Compressors;Clustering methods;Data mining;Application software;Astronomy;Dictionaries;Sorting;Heterogenous data analysis;hierarchical unsupervised clustering;Kolmogorov complexity;normalized compression distance;parameter-free data mining;quartet tree method;universal dissimilarity distance}
}

@Article{Cislak:2017,
  author    = {Cis{\l}ak, Aleksander and Grabowski, Szymon},
  title     = {Lightweight Fingerprints for Fast Approximate Keyword Matching Using Bitwise Operations},
  journal   = {CoRR},
  year      = {2017},
  volume    = {abs/1711.08475},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1711-08475},
  url       = {http://arxiv.org/abs/1711.08475},
}
@article{Clark:1952,
  title        = {An Extension of the Coefficient of Divergence for Use with Multiple Characters},
  author       = {Clark, {Philip J.}},
  year         = 1952,
  month        = jun,
  journal      = {Copeia},
  volume       = 1952,
  number       = 2,
  pages        = {61--64},
  doi          = {10.2307/1438532}
}
@article{Clement:1976,
  title        = {A Formula for Computing Inter-Observer Agreement},
  author       = {Clement, {Paul W.}},
  year         = 1976,
  journal      = {Psychological Reports},
  volume       = 39,
  number       = 1,
  pages        = {257--258},
  doi          = {10.2466/pr0.1976.39.1.257}
}
@article{Cohen:1960,
  title        = {A coefficient of agreement for nominal scales},
  author       = {Cohen, Jacob},
  year         = 1960,
  journal      = {Educational and Psychological Measurement},
  volume       = 20,
  number       = 1,
  pages        = {37--46},
  doi          = {10.1177/001316446002000104}
}
@inproceedings{Cohen:2003,
  title        = {A Comparison of String Distance Metrics for Name-Matching Tasks},
  author       = {Cohen, {William A.} and Ravikumar, Pradeep and Fienberg, {Stephen E.}},
  year         = 2003,
  booktitle    = {IIWEB'03 Proceedings of the 2003 International Conference on Information},
  pages        = {73--78},
  url          = {http://www.cs.cmu.edu/~wcohen/postscript/ijcai-ws-2003.pdf}
}
@misc{Cohen:2003b,
  title        = {SecondString},
  author       = {Cohen, {William W.} and Ravikumar, Pradeep and Fienberg, {Stephen E.} and Rivard, Kathryn},
  year         = 2003,
  url          = {https://github.com/TeamCohen/secondstring}
}
@misc{Cohen:2011,
  title        = {FuzzyWuzzy: Fuzzy String Matching in Python},
  author       = {Cohen, Adam},
  year         = 2011,
  month        = jul,
  url          = {https://chairnerd.seatgeek.com/fuzzywuzzy-fuzzy-string-matching-in-python/}
}
@article{Cole:1949,
  title        = {The Measurement of Interspecific Association},
  author       = {Cole, {Lamont C.}},
  year         = 1949,
  journal      = {Ecology},
  volume       = 30,
  number       = 4,
  pages        = {411--424},
  doi          = {10.2307/1932444}
}
@article{Connolly:1997,
  title        = {Quantifying target-realization differences},
  author       = {Connolly, {John H.}},
  year         = 1997,
  journal      = {Clinical Linguistics \& Phonetics},
  volume       = 11,
  number       = 4,
  pages        = {267--287},
  doi          = {10.3109/02699209708985195}
}
@article{Consonni:2012,
  title        = {New Similarity Coefficients for Binary Data},
  author       = {Consonni, Viviana and Todeschini, Roberto},
  year         = 2012,
  journal      = {MATCH Communications in Mathematical and in Computer Chemistry},
  volume       = 68,
  pages        = {581--592}
}
@inproceedings{Cormode:2000,
  title        = {Communication Complexity of Document Exchange},
  author       = {Cormode, Graham and Paterson, Mike and Sahinalp, {S\"{u}leyman Cenk} and Vishkin, Uzi},
  year         = 2000,
  booktitle    = {SODA '00 Proceedings of the eleventh annual ACM-SIAM symposium on Discrete algorithms},
  pages        = {197--200}
}
@phdthesis{Cormode:2003,
  title        = {Seuqnce Distance Embeddings},
  author       = {Cormode, Graham},
  year         = 2003,
  url          = {http://wrap.warwick.ac.uk/61310/7/WRAP\_THESIS\_Cormode\_2003.pdf},
  school       = {The University of Warwick}
}
@article{Covington:1996,
  title        = {An Algorithm to Align Words for Historical Comparison},
  author       = {Covington, {Michael A.}},
  year         = 1996,
  month        = dec,
  journal      = {Computational Linguistics},
  volume       = 22,
  number       = 4,
  pages        = {481--496}
}
@article{Cronbach:1951,
  title        = {Coefficient Alpha and the Internal Structure of Tests},
  author       = {Cronbach, {Lee J.}},
  year         = 1951,
  month        = sep,
  journal      = {Psychometrika},
  volume       = 16,
  number       = 3,
  pages        = {297--334},
  doi          = {10.1007/BF02310555}
}
@techreport{Cunningham:1969,
  title        = {A Study of the Organization and Search of Bibliographic Holdings in On-Line Computer Systems: Phase I},
  author       = {Cunningham, {Jay L.} and others},
  year         = 1969,
  month        = mar,
  url          = {https://files.eric.ed.gov/fulltext/ED029679.pdf},
  institution  = {University of California, Berkleley, Institute of Library Research}
}
@article{Czekanowski:1909,
  title        = {Zur Differentialdiagnose der Neandertalgruppe},
  author       = {Czekanowski, Jan},
  year         = 1909,
  journal      = {Korrespondenz-Blatt der Deutschen Gesellschaft f\"{u}r Anthropologie, Ethnologie und Urgeschichte},
  volume       = 40,
  pages        = {44--47}
}
@article{Dagan:1999,
  title        = {Similarity-Based Models of Word Cooccurrence Probabilities},
  author       = {Dagan, Ido and Lee, Lillian and Pereire, {Fernando C. N.}},
  year         = 1999,
  month        = feb,
  journal      = {Machine Learning},
  volume       = 34,
  number       = {1--3},
  pages        = {43--69},
  doi          = {10.1023/A:1007537716579}
}
@misc{Dalke:2005,
  title        = {Arithmetic Coder (Python Recipe)},
  author       = {Dalke, Andrew},
  year         = 2005,
  url          = {http://code.activestate.com/recipes/306626/}
}
@inproceedings{Dallmeier:2005,
  title        = {Lightweight},
  author       = {Dallmeier, Valentin and Lindig, Christian and Zeller, Andreas},
  year         = 2005,
  booktitle    = {ECOOP'05 Proceedings of the 19th European conference on Object-Oriented Programming},
  doi          = {10.1007/11531142\_23},
  url          = {https://www.st.cs.uni-saarland.de/papers/dlz2004/dlz2004.pdf}
}
@article{Damerau:1964,
  title        = {A Technique for Computer Detection and Correction of Spelling Errors},
  author       = {Damerau, {Fred J.}},
  year         = 1964,
  month        = mar,
  journal      = {Communications of the ACM},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 7,
  number       = 3,
  pages        = {171--176},
  doi          = {10.1145/363958.363994},
  issn         = {0001-0782},
  acmid        = 363994,
  issue_date   = {March 1964},
  numpages     = 6
}
@article{Davidson:1962,
  title        = {Retrieval of Misspelled Names in an Airlines Passenger Record System},
  author       = {Davidson, Leon},
  year         = 1962,
  month        = mar,
  journal      = {Communications of the ACM},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 5,
  number       = 3,
  pages        = {169--171},
  doi          = {10.1145/366862.366913},
  issn         = {0001-0782},
  acmid        = 366913,
  issue_date   = {March 1962},
  numpages     = 3
}
@misc{dcm4che:2011,
  title        = {{DICOM} Toolkit \& Library: Phonem.java},
  author       = {dcm4che},
  url          = {https://github.com/dcm4che/dcm4che/blob/master/dcm4che-soundex/src/main/java/org/dcm4che3/soundex/Phonem.java},
  organization = {dcm4che}
}
@inproceedings{delPilarAngeles:2015,
  title        = {Comparison of a Modified Spanish Phonetic, Soundex, and Phonex coding functions during data matching process},
  author       = {{del Pilar Angeles}, Mar{\'{i}}a and Espino-Gamez, Adri{\'{a}}n and Gil-Moncada, Jonathan},
  year         = 2015,
  month        = jun,
  booktitle    = {2015 International Conference on Informatics, Electronics Vision (ICIEV)},
  pages        = {1--5},
  doi          = {10.1109/ICIEV.2015.7334028},
  url          = {https://www.researchgate.net/publication/285589803\_Comparison\_of\_a\_Modified\_Spanish\_Phonetic\_Soundex\_and\_Phonex\_coding\_functions\_during\_data\_matching\_process},
  keywords     = {natural language processing;pattern matching;speech coding;phonex coding function;Spanish encoding function identification;data matching process;precision recall;f-measure;modified Spanish Phonetic Soundex function;phonetic coding function;Encoding;Indexing;Couplings;Prototypes;Measurement;Data visualization;data matching;de-duplication;record linkage}
}
@inproceedings{delPilarAngeles:2016,
  title        = {Performance of Spanish Encoding Functions during Record Linkage},
  author       = {{del Pilar Angeles}, Mar{\'{i}}a and Bail{\'{o}}n-Miguel, Noemi},
  year         = 2016,
  booktitle    = {DATA ANALYTICS 2016: The Fifth International Conference on Data Analysis},
  pages        = {1--7},
  url          = {https://core.ac.uk/download/pdf/55855695.pdf\#page=14}
}
@inproceedings{Dennis:1965,
  title        = {The Construction of a Thesaurus Automatic From a Sample of Text},
  author       = {Dennis, {Sally F.}},
  year         = 1965,
  month        = dec,
  booktitle    = {Statistical Association Techniques for Mechanized Documentation: Symposium Proceedings},
  address      = {Washington, D.C.},
  series       = {National Bureau of Standards Miscellaneous Publication},
  number       = 269,
  pages        = {61--148},
  url          = {https://archive.org/details/statisticalassoc269stev},
  editor       = {Stevens, {Mary Elizabeth} and Giuliano, {Vincent E.} and Heilprin, {Laurence B.}},
  organization = {United States Department of Commerce}
}
@book{Deza:2016,
  title        = {Encyclopedia of Distances},
  author       = {Deza, {Michel Marie} and Deza, Elena},
  year         = 2016,
  publisher    = {Springer-Verlag},
  address      = {Berlin},
  edition      = 4
}
@article{Dice:1945,
  title        = {Measures of the Amount of Ecologic Association Between Species},
  author       = {Dice, {Lee R.}},
  year         = 1945,
  journal      = {Ecology},
  volume       = 26,
  number       = 3,
  pages        = {297--302},
  doi          = {10.2307/1932409},
  url          = {https://www.jstor.org/stable/1932409}
}
@article{Digby:1983,
  title        = {Approximating the Tetrachoric Correlation Coefficient},
  author       = {Digby, {P. G. N.}},
  year         = 1983,
  month        = sep,
  journal      = {Biometrics},
  volume       = 39,
  number       = 3,
  pages        = {753--757},
  doi          = {10.2307/2531104}
}
@article{Dolby:1970,
  title        = {An Algorithm For Variable-Length Proper-Name Compression},
  author       = {Dolby, {James L.}},
  year         = 1970,
  journal      = {Journal of Library Automation},
  volume       = 3,
  number       = 4,
  pages        = {257--275},
  doi          = {10.6017/ital.v3i4.5259},
  url          = {https://ejournals.bc.edu/ojs/index.php/ital/article/download/5259/4734}
}

@Article{Doolittle:1884,
  author  = {Doolittle, {Mayrick H.}},
  title   = {The Verification of Predictions},
  journal = {The American Meteorological Journal},
  year    = {1884},
  volume  = {2},
  pages   = {327--329},
  url     = {https://books.google.com/books?id=2f0wAQAAMAAJ&pg=PA327},
}
@article{Downey:2008,
  title        = {Computational FeatureSensitive Reconstruction of Language Relationships: Developing the ALINE Distance for Comparative Historical Linguistic Reconstruction},
  author       = {Downey, {Sean S.} and Hallmark, Brian and Cox, {Murray P.} and Norquest, Peter and Lansing, {J. Stephen}},
  year         = 2008,
  month        = nov,
  journal      = {Journal of Quantitative Linguistics},
  volume       = 15,
  number       = 4,
  pages        = {340--369},
  doi          = {10.1080/09296170802326681}
}
@article{Downey:2017,
  title        = {alineR: an R Package for Optimizing Feature-Weighted Alignments and Linguistic Distances},
  author       = {Downey, {Sean S.} and Sun, Guowei and Norquest, Peter},
  year         = 2017,
  journal      = {The R Journal},
  volume       = 9,
  number       = 1,
  pages        = {138--152},
  doi          = {10.32614/RJ-2017-005},
  url          = {https://journal.r-project.org/archive/2017/RJ-2017-005/RJ-2017-005.pdf}
}
@article{Driver:1932,
  title        = {Quantitative Expression of Cultural Relationships},
  author       = {Driver, {Harold E.} and Kroeber, {Alfred L.}},
  year         = 1932,
  journal      = {University of California Publications in American Archaeology and Ethnology},
  publisher    = {University of California Press},
  volume       = 31,
  number       = 4,
  pages        = {211--256},
  url          = {http://digitalassets.lib.berkeley.edu/anthpubs/ucb/text/ucp031-005.pdf}
}
@article{Dunning:1993,
  title        = {Accurate Methods for the Statistics of Surprise and Coincidence},
  author       = {Dunning, Ted},
  year         = 1993,
  journal      = {Computational Linguistics},
  volume       = 19,
  number       = 1,
  pages        = {61--74},
  url          = {http://www.aclweb.org/anthology/J93-1003}
}
@article{Ehrenfeucht:1988,
  title        = {A new distance metric on strings computable in linear time},
  author       = {Ehrenfeucht, Andrzej and Haussler, David},
  year         = 1988,
  journal      = {Discrete Applied Mathematics},
  volume       = 20,
  number       = 3,
  pages        = {191--203},
  doi          = {10.1016/0166-218X(88)90076-5}
}
@book{Eidenberger:2014,
  title        = {Categorization and Machine Learning: The ModModel of Human Understanding in Computers},
  author       = {Eidenberger, Horst},
  year         = 2014,
  publisher    = {atpress}
}
@book{Ellenberg:1956,
  title        = {Grundlagen Der Vegetationsgliederung. Teil 1. Aufgaben Und Methoden Der Vegetationskunde},
  author       = {Ellenberg, Heinz},
  year         = 1956,
  publisher    = {Verlag Eugen Ulmer},
  address      = {Stuttgart}
}
@techreport{Elovitz:1976,
  title        = {Automatic Translation of English Text to PPhonetic by Means of Letter-to-Sound Rules},
  author       = {Elovitz, {Honey S.} and Johnson, {Rodney W.} and McHugh, Astrid and Shore, {John E.}},
  year         = 1976,
  address      = {Washington, D.C.},
  number       = {7948, document AD/A021 929},
  institution  = {Naval Research Laboratory},
  type         = {NRL Report}
}
@techreport{Erikson:1997,
  title        = {Approximate Swedish name matching - survey and test of different algorithms},
  author       = {Erikson, Klas},
  year         = 1997,
  address      = {Stockholm, Sweden},
  number       = {TRITA-NA-E9721},
  url          = {ftp://ftp.nada.kth.se/pub/documents/Theory/Viggo-Kann/NADA-E9721.pdf},
  institution  = {KTH, Royal Institute of Technology},
  type         = {Nada report}
}
@article{Eyraud:1938,
  title        = {Les principes de la mesure des corr{\'{e}}lations},
  author       = {Eyraud, Henri},
  year         = 1938,
  journal      = {Annales de l'Universit{/e} de Lyon, III Series, Section A},
  volume       = 1,
  pages        = {30--47}
}
@article{Fager:1957,
  title        = {Determination and Analysis of Recurrent Groups},
  author       = {Fager, {Edward W.}},
  year         = 1957,
  month        = oct,
  journal      = {Ecology},
  volume       = 38,
  number       = 4,
  pages        = {586--595},
  doi          = {10.2307/1943124}
}
@article{Fager:1963,
  title        = {Zooplankton Species Groups in the North Pacific},
  author       = {Fager, {Edward W.} and McGowan, {John A.}},
  year         = 1963,
  journal      = {Science},
  volume       = 140,
  number       = 3566,
  pages        = {453--460},
  doi          = {10.1126/science.140.3566.453}
}
@article{Faith:1983,
  title        = {Asymmetric Binary Similarity Measures},
  author       = {Faith, {Daniel P.}},
  year         = 1983,
  month        = mar,
  journal      = {Oecologia},
  volume       = 57,
  number       = 3,
  pages        = {287--290},
  doi          = {10.1007/BF00377169}
}
@article{Fleiss:1975,
  title        = {Measuring Agreement Between Two Judges on the Presence or Absence of a Trait},
  author       = {Fleiss, {Joseph L.}},
  year         = 1975,
  journal      = {Biometrics},
  volume       = 31,
  number       = 3,
  pages        = {651--659},
  doi          = {10.2307/2529549}
}
@book{Fleiss:2003,
  title        = {Statistical Methods for Rates and Proportions},
  author       = {Fleiss, {Joseph L.} and Levin, Bruce and Paik, {Myunghee Cho}},
  year         = 2003,
  publisher    = {John Wiley \& Sons},
  address      = {Hoboken},
  series       = {Wiley Series in Probability and Statistics},
  edition      = {3rd}
}
@article{Forbes:1907,
  title        = {On the Local Distribution of Certain Illinois Fishes: An Essay in Statistical Ecology},
  author       = {Forbes, {Stephen A.}},
  year         = 1907,
  journal      = {Bulletin of the Illinois State Laboratory of Natural History},
  volume       = 7,
  pages        = {273--303}
}
@article{Forbes:1925,
  title        = {Method of determining and measuring the associative relations of species},
  author       = {Forbes, {Stephen A.}},
  year         = 1925,
  journal      = {Science},
  volume       = 61,
  number       = 1585,
  pages        = {518--524}
}
@techreport{Fossum:1966,
  title        = {Optimization and Standardization of Information Retrieval Language and Systems},
  author       = {Fossum, {Earl G.} and Kaskey, Gilbert},
  year         = 1966,
  address      = {Washington, D.C.},
  url          = {https://archive.org/details/DTIC\_AD0630797},
  institution  = {Directorate of Information Sciences, Air Force Office of Scientific Research, Office of Aerospace Research, United States Air Force}
}
@article{Fowlkes:1983,
  title        = {A Method for Comparing Two Hierarchical Clusterings},
  author       = {Fowlkes, {E. B.} and Mallows, {Colin L.}},
  year         = 1983,
  journal      = {Journal of the American Statistical Association},
  volume       = 78,
  number       = 383,
  pages        = {553--569},
  doi          = {10.1080/01621459.1983.10478008}
}
@article{Furnohr:2002,
  title        = {Zusammenf{\"{u}}hrung von Datenbest{\"{a}}nden ohne numerische Identifikatoren: ein Verfahren im Rahmen der Testuntersuchungen zu einem registergest{\"{u}}tzten Zensus},
  author       = {F{\"{u}}rnrohr, Michael and Rimmelspacher, Birgit and von Roncador, Tilman},
  year         = 2002,
  journal      = {Bayern in Zahlen},
  volume       = 2002,
  number       = 7,
  pages        = {308--321},
  url          = {https://www.statistik.bayern.de/medien/statistik/zensus/zusammenf\_\_hrung\_von\_datenbest\_\_nden\_ohne\_numerische\_identifikatoren.pdf}
}
@article{Gadd:1990,
  title        = {PHONIX: The algorithm},
  author       = {Gadd, {T. N.}},
  year         = 1990,
  journal      = {Program},
  volume       = 24,
  number       = 4,
  pages        = {363--366},
  doi          = {10.1108/eb047069}
}
@misc{Garshol:2015,
  title        = {Norphone Comparator},
  author       = {Garshol, {Lars Marius}},
  year         = 2015,
  url          = {https://github.com/larsga/Duke/blob/master/duke-core/src/main/java/no/priv/garshol/duke/comparators/NorphoneComparator.java}
}
@misc{Getty:1991,
  title        = {Synoname},
  author       = {{J. Paul Getty Trust}, The},
  year         = 1991,
  address      = {Los Angeles},
  url          = {http://www.cs.cmu.edu/Groups/AI/areas/nlp/misc/synoname/synoname.zip},
  organization = {The J. Paul Getty Trust}
}
@article{Gilbert:1884,
  title        = {Finley's Tornado Predictions},
  author       = {Gilbert, {Grove K.}},
  year         = 1884,
  journal      = {American Meteorological Journal},
  volume       = 1,
  pages        = {166--172}
}
@article{Gilbert:1966,
  title        = {Analysis of Quadrat Data},
  author       = {Gilbert, N. and Wells, {Terry C. E.}},
  year         = 1966,
  month        = nov,
  journal      = {Journal of Ecology},
  volume       = 54,
  number       = 3,
  pages        = {675--685},
  doi          = {10.2307/2257810}
}
@inproceedings{Gill:1997,
  title        = {OX-LINK: The Oxford Medical Record Linkage System},
  author       = {Gill, {Leicester E.}},
  year         = 1997,
  month        = mar,
  booktitle    = {Record Linkage Techniques},
  publisher    = {Office of Management and Budget},
  address      = {Washington, D.C.},
  url          = {https://pdfs.semanticscholar.org/fff7/02a3322e05c282a84064ee085e589ef74584.pdf},
  organization = {Federal Committee on Statistical Methodology}
}
@book{Gini:1912,
  title        = {Variabilit{\`{a}} e mutabilit{\`{a}}},
  author       = {Gini, Corrado},
  year         = 1912,
  publisher    = {C. Cuppini},
  address      = {Bologna},
  series       = {Contributo allo Studio delle Distribuzioni e delle Relazioni Statistiche}
}
@article{Gini:1915,
  title        = {Nuovi contributi all teoria delle relazioni statistiche},
  author       = {Gini, Corrado},
  year         = 1915,
  journal      = {Atti del Reale Istituto Veneto di Scienze, Lettere ed Arti, Series 8},
  volume       = 74,
  number       = 2,
  pages        = {1903--1942}
}
@article{Gleason:1920,
  title        = {Some Applications of the Quadrat Method},
  author       = {Gleason, {Henry Allan}},
  year         = 1920,
  month        = jan,
  journal      = {Bulletin of the Torrey Botanical Club},
  volume       = 47,
  number       = 1,
  pages        = {21--33},
  doi          = {10.2307/2480223}
}
@article{Goodall:1967,
  title        = {The Distribution of the Matching Coefficient},
  author       = {Goodall, {David W.}},
  year         = 1967,
  month        = dec,
  journal      = {Biometrics},
  volume       = 23,
  number       = 4,
  pages        = {647--656},
  doi          = {10.2307/2528419}
}
@article{Goodman:1954,
  title        = {Measures of Association for Cross Classification I},
  author       = {Goodman, {Leo A.} and Kruskal, {William H.}},
  year         = 1954,
  journal      = {Journal of the American Statistical Association},
  volume       = 49,
  number       = 268,
  pages        = {732--764},
  doi          = {10.2307/2281536}
}
@article{Goodman:1959,
  title        = {Measures of Association for Cross Classification II: Further Discussion and References},
  author       = {Goodman, {Leo A.} and Kruskal, {William H.}},
  year         = 1959,
  month        = mar,
  journal      = {Journal of the American Statistical Association},
  volume       = 54,
  number       = 285,
  pages        = {123--163},
  doi          = {10.2307/2282143}
}
@article{Goodman:1963,
  title        = {Measures of Association for Cross Classification III: Approximate Sampling Theory},
  author       = {Goodman, {Leo A.} and Kruskal, {William H.}},
  year         = 1963,
  journal      = {Journal of the American Statistical Association},
  volume       = 55,
  number       = 302,
  pages        = {310--364},
  doi          = {10.1080/01621459.1963.10500850}
}
@article{Gotoh:1982,
  title        = {An improved algorithm for matching biological sequences},
  author       = {Gotoh, Osamu},
  year         = 1982,
  journal      = {Journal of Molecular Biology},
  volume       = 162,
  number       = 3,
  pages        = {705--708},
  doi          = {10.1016/0022-2836(82)90398-9},
  issn         = {0022-2836},
  url          = {http://www.sciencedirect.com/science/article/pii/0022283682903989}
}
@article{Gower:1971,
  title        = {A General Coefficient of Similarities and Some of Its Properties},
  author       = {Gower, {John C.}},
  year         = 1971,
  month        = dec,
  journal      = {Biometrics},
  volume       = 27,
  number       = 4,
  pages        = {857--871},
  doi          = {10.2307/2528823}
}
@article{Gower:1986,
  title        = {Metric and {Euclid}ean Properties of Dissimilarity Coefficients},
  author       = {Gower, {John C.} and Legendre, Pierre},
  year         = 1986,
  month        = feb,
  journal      = {Journal of Classification},
  volume       = 3,
  number       = 1,
  pages        = {5--48},
  doi          = {10.1007/BF01896809}
}
@inproceedings{Gravano:2001,
  title        = {Approximate String Joins in a Database (Almost) for Free},
  author       = {Gravano, Luis and Ipeirotis, {Panagiotis G.} and Jagadish, {H. V.} and Koudas, Nick and Muthukrishman, {S.} and Srivastava, Divesh},
  year         = 2001,
  booktitle    = {Proceedings of the 27th VLDB Conference, Roma, Italy, 2001}
}
@inproceedings{Gross:1991,
  title        = {Getty Synoname: The Development of Software for Personal Name Pattern Matching},
  author       = {Gross, {Aaron D.}},
  year         = 1991,
  booktitle    = {Intelligent Text and Image Handling - Volume 2},
  location     = {Barcelona, Spain},
  publisher    = {LE CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE},
  address      = {Paris, France, France},
  series       = {RIAO '91},
  pages        = {754--763},
  url          = {http://dl.acm.org/citation.cfm?id=3171004.3171021},
  acmid        = 3171021,
  numpages     = 10
}
@book{Guilford:1956,
  title        = {Fundamental Statistics in Psychology and Education},
  author       = {Guildford, {J. P.}},
  year         = {New York},
  publisher    = {McGraw-Hill Book Company},
  address      = {New York},
  url          = {https://archive.org/details/in.ernet.dli.2015.228996}
}
@article{Guth:1976,
  title        = {Surname Spellings and Computerized Record Linkage},
  author       = {Guth, {Gloria J. A.}},
  year         = 1976,
  journal      = {Historical Methods Newsletter},
  volume       = 10,
  number       = 1,
  pages        = {10--19},
  doi          = {10.1080/00182494.1976.10112645}
}
@incollection{Guttman:1941,
  title        = {An Outline of the Statistical Theory of Prediction},
  author       = {Guttman, Louis},
  year         = 1941,
  booktitle    = {The Prediction of Personal Adjustment},
  publisher    = {Social Science Research Council},
  number       = 48,
  pages        = {253--311},
  url          = {https://babel.hathitrust.org/cgi/pt?id=uc1.b4579784;view=1up;seq=271},
  editor       = {Horst, Paul}
}
@article{Gwet:2008,
  title        = {Computing inter-rater reliability and its variance in the presence of high agreement},
  author       = {Gwet, {Kilem Li}},
  year         = 2008,
  journal      = {British Journal of Mathematical and Statistical Psychology},
  volume       = 61,
  number       = 1,
  pages        = {29--48},
  doi          = {10.1348/000711006X126600}
}
@misc{Haase:2000,
  title        = {Die Erweiterte K{\"{o}}lner Phonetik},
  author       = {Haase, Martin and Heitmann, Kai},
  year         = 2000
}
@article{Hamann:1961,
  title        = {Merkmalbestand und Verwandtschaftsbeziehungen der Farinosae: ein Beitrag zum System der Monokotyledonen},
  author       = {Hamann, Ulrich},
  year         = 1961,
  journal      = {Willdenowia},
  volume       = 2,
  pages        = {639--768}
}
@article{Hamming:1950,
  title        = {Error detecting and error correcting codes},
  author       = {Hamming, {R. W.}},
  year         = 1950,
  month        = apr,
  journal      = {The Bell System Technical Journal},
  volume       = 29,
  number       = 2,
  pages        = {147--160},
  doi          = {10.1002/j.1538-7305.1950.tb00463.x},
  issn         = {0005-8580},
  url          = {https://ieeexplore.ieee.org/document/6772729/}
}
@article{Harman:1991,
  title        = {How Effective Is Stemming?},
  author       = {Harman, Donna},
  year         = 1991,
  journal      = {Journal of the American Society for Information Science},
  volume       = 42,
  number       = 1,
  pages        = {7--15},
  doi          = {10.1002/(SICI)1097-4571(199101)42:1\%3C7::AID-ASI2\%3E3.0.CO;2-P},
  url          = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.104.9828\&rep=rep1\&type=pdf}
}
@article{Harris:1978,
  title        = {A Method for Combining Occurrence and Nonoccurrence Interobserver Agreement Scores},
  author       = {Harris, {Francis C.} and Lahey, {Benjamin B.}},
  year         = 1978,
  journal      = {Journal of Applied Behavior Analysis},
  volume       = 11,
  number       = 4,
  pages        = {523--527},
  doi          = {10.1901/jaba.1978.11-523}
}
@article{Hassanat:2014,
  title        = {Dimensionality Invariant Similarity Measure},
  author       = {Hassanat, {Ahmad Basheer}},
  year         = 2014,
  journal      = {Journal of American Science},
  volume       = 10,
  number       = 8,
  pages        = {221--226},
  url          = {https://arxiv.org/abs/1409.0923}
}
@techreport{Hawkins:1973,
  title        = {Reliability Scores That Delude: An Alice in Wonderland Trip Through the Misleading Characteristics of Inter-Observer Agreement Scores in Interval Recording},
  author       = {Hawkins, {Robert P.} and Dotson, {Victor A.}},
  year         = 1973,
  url          = {https://eric.ed.gov/?id=ED094277},
  institution  = {Western Michigan University}
}
@article{Hellinger:1909,
  title        = {Neue Begr{\"{u}}ndung der Theorie quadratischer Formen von unendlichvielen Ver{\"{a}}nderlichen},
  author       = {Hellinger, Ernst},
  year         = 1909,
  journal      = {Journal F\"{u}r Die Reine Und Angewandte Mathematik},
  volume       = 1909,
  number       = 136,
  pages        = {210--271},
  doi          = {10.1515/crll.1909.136.210}
}
@article{Henderson:1977,
  title        = {A probabilistic method of paleobiogeographic analysis},
  author       = {Henderson, {Robert A.} and Heron, {Malcolm L.}},
  year         = 1977,
  journal      = {Lethaia},
  volume       = 10,
  number       = 1,
  pages        = {1--15},
  doi          = {10.1111/j.1502-3931.1977.tb00584.x}
}
@article{Henry:1976,
  title        = {Projet de transcription phon{\'{e}}tique des noms de famille},
  author       = {Henry, Louis},
  year         = 1976,
  journal      = {Annales de D\'{e}mographie Historique},
  volume       = 1976,
  pages        = {201--214},
  url          = {https://www.persee.fr/doc/adh\_0066-2062\_1976\_num\_1976\_1\_1313}
}
@article{Hershberg:1976,
  title        = {Record Linkage},
  author       = {Hershberg, Theodore and Burstein, Alan and Dockhorn, Robert},
  year         = 1976,
  journal      = {Historical Methods Newsletter},
  volume       = 9,
  number       = {2--3},
  pages        = {137--163},
  doi          = {10.1080/00182494.1976.10112639}
}
@incollection{Hershberg:1979,
  title        = {Verkettung von Daten: Record Linkage am Beispiel des Philadelphia Social History Project},
  author       = {Hershberg, Theodore and Burstein, Alan and Dockhorn, Robert},
  year         = 1979,
  booktitle    = {Moderne Stadtgeschichte},
  publisher    = {Klett-Cotta},
  volume       = 8,
  pages        = {35--73},
  isbn         = {3-12-911080-1},
  url          = {https://www.ssoar.info/ssoar/handle/document/32782},
  editor       = {Schr\"{o}der, {Wilhelm Heinz}},
  urn          = {http://nbn-resolving.de/urn:nbn:de:0168-ssoar-327824}
}
@inproceedings{Higuera:2008,
  title        = {A Contextual Normalised Edit Distance},
  author       = {{de la Higuera}, Colin and Mic\'{o}, Luisa},
  year         = 2008,
  booktitle    = {First International Workshop on Similarity Search and Applications (sisap 2008)},
  doi          = {10.1109/SISAP.2008.17}
}
@inproceedings{Holmes:2002,
  title        = {Improving precision and recall for Soundex retrieval},
  author       = {Holmes, David and McCabe, {M. Catherine}},
  year         = 2002,
  month        = apr,
  booktitle    = {Proceedings. International Conference on Information Technology: Coding and Computing},
  pages        = {22--26},
  doi          = {10.1109/ITCC.2002.1000354},
  url          = {https://ieeexplore.ieee.org/document/1000354/},
  keywords     = {relevance feedback;linguistics;precision;recall;Soundex retrieval;phonetic algorithm;name searches;phonetic codes;digrams;Dice coefficient;similarity score;Pfeifer corpus;relevance assessments;Information retrieval;Computer errors;Government;Fuses;Information systems;Libraries;Cultural differences;Information technology}
}
@techreport{Hood:2002,
  title        = {CaveSystem: Phonetic Matching algorithm},
  author       = {Hood, David},
  year         = 2002,
  month        = sep,
  address      = {Dunedin, New Zealand},
  number       = {CTP060902},
  url          = {https://caversham.otago.ac.nz/files/working/ctp060902.pdf},
  institution  = {University of Otago}
}
@techreport{Hood:2004,
  title        = {Caverphone Revisited},
  author       = {Hood, David},
  year         = 2004,
  month        = dec,
  address      = {Dunedin, New Zealand},
  number       = {CTP150804},
  url          = {https://caversham.otago.ac.nz/files/working/ctp150804.pdf},
  institution  = {University of Otago}
}
@article{Horn:1966,
  title        = {Measurement of "Overlap" in Comparative Ecological Studies},
  author       = {Horn, {Henry S.}},
  year         = 1966,
  month        = sep,
  journal      = {The American Naturalist},
  volume       = 100,
  number       = 914,
  pages        = {419--424},
  doi          = {10.2307/2459242}
}
@article{Hubalek:1982,
  title        = {Coefficients of Association and Similarity, Based on Binary (Presence-Absence) Data: An Evaluation},
  author       = {Hub{\'{a}}lek, Zdenek},
  year         = 2008,
  month        = feb,
  journal      = {Biological Reviews},
  volume       = 57,
  number       = 4,
  pages        = {669--689},
  doi          = {10.1111/j.1469-185X.1982.tb00376.x}
}
@article{Hurlbert:1969,
  title        = {A Coefficient of Interspecific Assciation},
  author       = {Hurlbert, {Stuart H.}},
  year         = 1969,
  month        = jan,
  journal      = {Ecology},
  volume       = 50,
  number       = 1,
  pages        = {1--9},
  doi          = {10.2307/1934657}
}
@manual{IBM:1973,
  title        = {Alpha Search Inquiry System, General Information Manual},
  author       = {IBM Corporation},
  year         = 1973,
  address      = {White Plains, NY}
}
@book{IBM:2017,
  title        = {{IBM SPS}S Statistics Algorithms},
  author       = {IBM Corporation},
  year         = 2017,
  publisher    = {IBM Corporation},
  url          = {ftp://public.dhe.ibm.com/software/analytics/spss/documentation/statistics/subscription/en/client/Manuals/IBM\_SPSS\_Statistics\_Algorithms.pdf},
  edition      = 25
}
@article{Jaccard:1901,
  title        = {Distribution de la flore alpine dans le bassin des Dranses et dans quelques r{\'{e}}gions voisines},
  author       = {Jaccard, Paul},
  year         = 1901,
  journal      = {Bulletin de la Soci\'{e}t\'{e} Vaudoise des Sciences Naturelles},
  volume       = 37,
  pages        = {241--272},
  url          = {https://core.ac.uk/download/pdf/20654241.pdf}
}
@article{Jaro:1989,
  title        = {Advances in record linkage methodology as applied to the 1985 census of Tampa Florida},
  author       = {Jaro, {Matthew A.}},
  year         = 1989,
  journal      = {Journal of the American Statistical Association},
  volume       = 84,
  number       = 406,
  pages        = {414--420},
  doi          = {10.1080/01621459.1989.10478785}
}
@techreport{Jenkins:2005,
  title        = {Conservative stemming for search and indexing},
  author       = {Jenkins, Marie-Claire and Smith, Dan},
  year         = 2005,
  address      = {Norwich, UK},
  url          = {http://lemur.cmp.uea.ac.uk/Research/stemmer/stemmer25feb.pdf},
  institution  = {University of East-Anglia}
}
@inproceedings{Jiminez:2013,
  title        = {{SOFTCARDINALITY-CORE}: Improving Text Overlap with Distributional Measures for Semantic Textual Similarity},
  author       = {Jiminez, Sergio and Becerra, Claudio and Gelbukh, Alexander},
  year         = 2013,
  month        = jun,
  booktitle    = {Second Joint Conference on Lexical and Computational Semantics (\textasteriskcenteredSEM), Volume 1: Proceedings of the Main Conference and the Shared Task},
  publisher    = {Association for Computational Linguistics},
  address      = {Atlanta, GA},
  pages        = {194--201},
  url          = {http://www.aclweb.org/anthology/S13-1028}
}
@article{Johnson:1967,
  title        = {Hierarchical Clustering Schemes},
  author       = {Johnson, {Stephen C.}},
  year         = 1967,
  month        = sep,
  journal      = {Psychometrika},
  volume       = 32,
  number       = 3,
  pages        = {241--254},
  doi          = {10.1007/BF02289588}
}
@inproceedings{Jones:2005,
  title        = {Empirical Evaluation of the Tarantula Automatic Fault-Localization Technique},
  author       = {Jones, {James A.} and Harrold, {Mary Jean}},
  year         = 2005,
  month        = nov,
  booktitle    = {ASE '05 Proceedings of the 20th IEEE/ACM international Conference on Automated software engineering},
  location     = {Long Beach, CA, USA},
  publisher    = {ACM},
  address      = {New York},
  pages        = {273--282},
  doi          = {10.1145/1101908.1101949},
  isbn         = {1-58113-993-4},
  organization = {ACM}
}
@mastersthesis{Kempken:2005,
  title        = {Bewertung historischer und regionaler Schreibvarianten mit Hilfe von Abstandsma\ss{}en},
  author       = {Kempken, Sebastian},
  year         = 2005,
  month        = dec,
  url          = {https://duepublico.uni-duisburg-essen.de/servlets/DerivateServlet/Derivate-17252/BewertungSchreibvarianten.pdf},
  school       = {Universit\"{a}t Duisburg-Essen}
}
@article{Kendall:1938,
  title        = {A New Measure of Rank Correlation},
  author       = {Kendall, {Maurice G.}},
  year         = 1938,
  month        = jun,
  journal      = {Biometrika},
  volume       = 30,
  number       = {1/2},
  pages        = {81--93},
  doi          = {10.2307/2332226}
}
@incollection{Kent:1977,
  title        = {Direct Observational Procedure: Methodological Issues in Naturalistic Settings},
  author       = {Kent, {Ronald N.} and Foster, {Sharon L.}},
  year         = 1977,
  booktitle    = {Handbook of Behavioral Assessment},
  publisher    = {John Wiley \& Sons},
  address      = {New York},
  pages        = {279--328},
  url          = {https://archive.org/details/handbookofbehavi00cimi},
  chapter      = 9,
  editor       = {Ciminero, {Anthony R.} and Calhoun, {Karen, S.} and Adams, {Henry E.}}
}
@inbook{Knuth:1998,
  title        = {The Art of Computer Programming: Volume 3, Sorting and Searching},
  author       = {Knuth, {Donald E.}},
  year         = 1998,
  publisher    = {Addison-Wesley},
  pages        = 394
}
@misc{Kollar:2007,
  title        = {Text::Phonetic::Phonix},
  author       = {Koll{\'{a}}r, Maro{\v{s}}},
  url          = {https://github.com/maros/Text-Phonetic/blob/master/lib/Text/Phonetic/Phonix.pm}
}
@inproceedings{Kondrak:2000,
  title        = {A New Algorithm for the Alignment of Phonetic Sequences},
  author       = {Kondrak, Grzegorz},
  year         = 2000,
  booktitle    = {NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference},
  doi          = {10.0000/dl.acm.org/974343}
}
@phdthesis{Kondrak:2002,
  title        = {Algorithms for Language Reconstruction},
  author       = {Kondrak, Grzegorz},
  year         = 2002,
  url          = {https://webdocs.cs.ualberta.ca/~kondrak/papers/thesis.pdf},
  school       = {University of Toronto}
}
@techreport{Kondrak:2003,
  title        = {A Similarity-Based Approach and Evaluation Methodology for Reduction of Drug Name Confusion},
  author       = {Kondrak, Grzegorz and Dorr, {Bonnie J.}},
  year         = 2003,
  url          = {https://apps.dtic.mil/dtic/tr/fulltext/u2/a452242.pdf},
  institution  = {University of Maryland, Institute for Advanced Computer Studies}
}
@inproceedings{Kondrak:2004,
  title        = {Identification of Confusable Drug Names: A New Approach and Evaluation Methodology},
  author       = {Kondrak, Grzegorz and Door, {Bonnie J.}},
  year         = 2004,
  booktitle    = {Proceedings of the 20th International Conference on Computational Linguistics - COLING '04},
  doi          = {10.3115/1220355.1220492}
}
@inproceedings{Koneru:2017,
  title        = {Privacy Preserving Record Linkage Using MetaSoundex Algorithm},
  author       = {Koneru, Kerrthi and Varol, Cihan},
  year         = 2017,
  month        = dec,
  booktitle    = {2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)},
  pages        = {443--447},
  doi          = {10.1109/ICMLA.2017.0-121},
  url          = {https://ieeexplore.ieee.org/document/8260671/}
}
@incollection{Koppen:1870,
  title        = {Die Aufeinanderfolge der Periodischen Witterungserscheinungen nach den Grunds{\"{a}}tzen der Wahrscheinlichkeitsrechnung},
  author       = {K{\"{o}}ppen, Wladimir},
  year         = 1870,
  booktitle    = {Repertorium f\"{u}r Meteorologie},
  publisher    = {Akademiia Nauk},
  volume       = 2,
  pages        = {189--238},
  url          = {https://books.google.com/books?id=1ww0AQAAMAAJ\&pg=RA1-PA187\#v=onepage\&q\&f=false}
}
@article{Koppen:1884,
  title        = {Eine Rationelle Methode zur Pr{\"{u}}fung der Wetterprognosen},
  author       = {K{\"{o}}ppen, Wladimir},
  year         = 1884,
  journal      = {Meteorologische Zeitschrif},
  volume       = 1
}
@article{Kuder:1937,
  title        = {The Theory of the Estimation of Test Reliability},
  author       = {Kuder, {G. Frederic} and Richardson, {Marion Webster}},
  year         = 1937,
  month        = sep,
  journal      = {Psychometrika},
  volume       = 2,
  number       = 3,
  pages        = {151--160},
  doi          = {10.1007/bf02288391}
}
@misc{Kuhn:1995,
  title        = {Metaphone searches},
  author       = {Kuhn, Michael},
  year         = 1995,
  month        = nov,
  url          = {http://aspell.net/metaphone/metaphone-kuhn.txt}
}
@inproceedings{Kuhns:1965,
  title        = {The Continuum of Coefficients of Association},
  author       = {Kuhns, {John L.}},
  year         = 1964,
  booktitle    = {Statistical Association Methods for Mechanized Documentation},
  series       = {National Bureau of Standards Miscellaneous Publication},
  number       = 269,
  pages        = {33--40},
  editor       = {Stevens, {Mary Elizabeth} and Giuliano, {Vincent E.} and Heilprin, {Laurence B.}}
}
@misc{Kula:2015,
  title        = {Simple MinHash implementation in Python},
  author       = {Kula, Maciej},
  year         = 2015,
  month        = jun,
  url          = {https://maciejkula.github.io/2015/06/01/simple-minhash-implementation-in-python/}
}
@article{Kulczynski:1927,
  title        = {Die Pflanzenassoziationen der Pieninen},
  author       = {Kulczyn\'ski, Stanis{\l}aw},
  year         = 1927,
  journal      = {Bulletin International de l'Academie Polonaise des Sciences et des Lettres, Classe des Sciences Mathematiques et Naturelles, B (Sciences Naturelles)},
  pages        = {57--203}
}
@article{Kullback:1951,
  title        = {On Information and Sufficiency},
  author       = {Kullback, {S. A.} and Leibler, {R. A.}},
  year         = 1951,
  journal      = {The Annals of Mathematical Statistics},
  volume       = 22,
  number       = 1,
  pages        = {79--86},
  doi          = {10.1214/aoms/1177729694},
  url          = {https://projecteuclid.org/euclid.aoms/1177729694}
}
@book{Ladefoged:1995,
  title        = {A Course in Phonetics},
  author       = {Ladefoged, Peter},
  year         = 1995,
  publisher    = {Harcourt Brace Jovanovich},
  address      = {New York}
}
@techreport{Lait:1996,
  title        = {An Assessment of Name Matching Algorithms},
  author       = {Lait, {Andrew J.} and Randell, Brian},
  year         = 1996,
  address      = {Newcastle upon Tyne, UK},
  url          = {http://homepages.cs.ncl.ac.uk/brian.randell/Genealogy/NameMatching.pdf},
  institution  = {University of Newcastle upon Tyne}
}
@article{Lance:1966,
  title        = {Computer programs for hierarchical polythetic classification ("similarity analysis")},
  author       = {Lance, {Godfrey N.} and Williams, {William T.}},
  year         = 1966,
  journal      = {Computer Journal},
  volume       = 9,
  number       = 1,
  doi          = {10.1093/comjnl/9.1.60}
}
@article{Lance:1967,
  title        = {A general theory of classificatory sorting strategies. II. Clustering systems.},
  author       = {Lance, {Godfrey N.} and Williams, {William T.}},
  year         = 1967,
  month        = jan,
  journal      = {Computer Journal},
  volume       = 10,
  number       = 3,
  pages        = {271--277},
  doi          = {10.1093/comjnl/10.3.271},
  url          = {https://academic.oup.com/comjnl/article-pdf/10/3/271/1333425/100271.pdf}
}
@article{Lance:1967b,
  title        = {Mixed-data classificatory programs I. Agglomerative systems},
  author       = {Lance, {Godfrey N.} and Williams, {William T.}},
  year         = 1967,
  journal      = {Australian Computer Journal},
  volume       = 1,
  pages        = {15--20}
}
@misc{Lang:2013,
  title        = {Inner wworking of the German Analyzer in Lucene},
  author       = {Lang, Joerg},
  year         = 2013,
  month        = nov,
  url          = {http://www.evelix.ch/unternehmen/Blog/evelix/2013/11/11/inner-workings-of-the-german-analyzer-in-lucene}
}
@article{Legare:1972,
  title        = {The Early Canadian Population: Problems in Automatic Record Linkage},
  author       = {L{\'{e}}gar{\'{e}}, Jacques and Lavoie, Yolande and Charbonneau, Hubert},
  year         = 1972,
  month        = dec,
  journal      = {Canadian Historical Review},
  volume       = 53,
  number       = 4,
  pages        = {427--442},
  doi          = {10.3138/CHR-053-04-03}
}
@book{Legendre:1998,
  title        = {Numerical Ecology},
  author       = {Legendre, Pierre and Legendre, Louis},
  year         = 1998,
  publisher    = {Elsevier},
  address      = {Amsterdam},
  series       = {Developments in Environmental Modelling},
  number       = 20,
  edition      = {2nd}
}
@article{Levenshtein:1965,
  title        = {Binary codes capable of correcting deletions, insertions, and reversals},
  author       = {Levenshtein, {Vladimir I.}},
  year         = 1965,
  journal      = {Doklady Akademii Nauk SSSR},
  volume       = 163,
  number       = 4,
  pages        = {845--848},
  url          = {http://mi.mathnet.ru/dan31411}
}
@article{Levenshtein:1966,
  title        = {Binary codes capable of correcting deletions, insertions, and reversals},
  author       = {Levenshtein, {Vladimir I.}},
  year         = 1966,
  month        = feb,
  journal      = {Soviet Physics Doklady},
  volume       = 10,
  number       = 8,
  pages        = {707--710},
  url          = {https://nymity.ch/sybilhunting/pdf/Levenshtein1966a.pdf}
}
@inproceedings{Lin:2004,
  title        = {ROUGE: A Package for Automatic Evaluation of Summaries},
  author       = {Lin, Chin-Yew},
  year         = 2004,
  booktitle    = {Text Summarization Branches Out},
  url          = {http://aclweb.org/anthology/W04-1013}
}
@book{LOC:2013,
  title        = {Classification and Shelflisting Manual},
  author       = {Library of Congress},
  year         = 2013,
  publisher    = {Library of Congress},
  url          = {https://www.loc.gov/aba/publications/FreeCSM/freecsm.html}
}
@article{Lodhi:2002,
  title        = {Text Classification using String Kernels},
  author       = {Lodhi, Huma and Saunders, Craig and {Shawe-Taylor}, John and Cristianini, Nello and Watkins, Chris},
  year         = 2002,
  journal      = {Journal of Machine Learning Research},
  volume       = 2,
  pages        = {419--444},
  doi          = {10.1162/153244302760200687}
}
@article{Lovins:1968,
  title        = {Development of a Stemming Algorithm},
  author       = {Lovins, {Julie Beth}},
  year         = 1968,
  month        = jun,
  journal      = {Mechanical Translation and Computational Linguistics},
  volume       = 11,
  number       = {1--2},
  pages        = {22--31},
  url          = {http://www.mt-archive.info/MT-1968-Lovins.pdf}
}
@techreport{Lynch:1977,
  title        = {Selection of a Surname Coding Procedure for the SRS Record Linkage System},
  author       = {Lynch, {Billy T.} and Arends, {William L.}},
  year         = 1977,
  month        = feb,
  address      = {Washington, D.C.},
  url          = {https://naldc.nal.usda.gov/download/27833/PDF},
  institution  = {Statistical Reporting Service, US Department of Agriculture}
}
@article{Maarel:1969,
  title        = {On the Use of Ordination Model in Phytosociology},
  author       = {{van der Maarel}, Eddy},
  year         = 1969,
  month        = jan,
  journal      = {Vegetatio Acta Geobotanica},
  volume       = 19,
  number       = {1--6},
  pages        = {21--46}
}
@misc{Marcelino:2015,
  title        = {SoundexBR: Soundex (Phonetic) Algorithm For {Brazil}ian Portuguese},
  author       = {Marcelino, Daniel},
  year         = 2015,
  month        = jul,
  url          = {https://github.com/danielmarcelino/SoundexBR}
}
@article{Maron:1960,
  title        = {On Relevance, Probabilistic Indexing and Information Retrieval},
  author       = {Maron, {Melvin E.} and Kuhns, {John L.}},
  year         = 1960,
  journal      = {Journal of the ACM},
  volume       = 7,
  number       = 3,
  pages        = {216--244},
  doi          = {10.1145/321033.321035}
}
@article{Matthews:1975,
  title        = {Comparison of the predicted and observed secondary structure of T4 phage lysozyme},
  author       = {Matthews, {Brian W.}},
  year         = 1975,
  journal      = {Biochimica et Biophysica Acta (BBA) - Protein Structure},
  volume       = 405,
  number       = 2,
  pages        = {442--451}
}
@article{Matusita:1955,
  title        = {Decision Rules, Based on the Distance, for Problems of Fit, Two Samples, and Estimation},
  author       = {Matusita, Kameo},
  year         = 1955,
  month        = dec,
  journal      = {The Annals of Mathematical Statistics},
  volume       = 26,
  number       = 4,
  pages        = {631--640},
  doi          = {10.2307/2236376}
}
@article{Maxwell:1968,
  title        = {Deriving Coefficients of Reliability and Agreement for Ratings},
  author       = {Maxwell, {A. E.} and Pilliner, {A. E. G.}},
  year         = 1968,
  month        = may,
  journal      = {The British Journal of Mathematical and Statistical Psychology},
  volume       = 21,
  number       = 1,
  pages        = {105--116},
  doi          = {10.1111/j.2044-8317.1968.tb00401.x}
}
@article{McConnaughey:1964,
  title        = {The Determination and Analysis of Plankton Communities},
  author       = {McConnaughey, {Bayard H.}},
  year         = 1964,
  journal      = {Lembaga Penelitian Laut},
  number       = {Special Number},
  pages        = {1--40}
}
@article{Merity:2016,
  title        = {Pointer Sentinel Mixture Models},
  author       = {Merity, Stephen and Xiong, Caiming and Bradbury, James and Socher, Richard},
  year         = 2016,
  journal      = {CoRR},
  volume       = {abs/1609.07843},
  url          = {http://arxiv.org/abs/1609.07843}
}
@article{Michael:1920,
  title        = {Marine Ecology and the Coefficient of Association: A Plea in Behalf of Quantitative Biology},
  author       = {Michael, {Ellis L.}},
  year         = 1920,
  journal      = {The Journal of Ecology},
  volume       = 8,
  number       = 1,
  pages        = {54--59},
  doi          = {10.2307/2255213}
}
@article{Michael:1999,
  title        = {Doppelg{\"{a}}nger gesucht -- Ein Programm f{\"{u}}r die kontextsensitive phonetische Stringumwandlung},
  author       = {Michael, J{\"{o}}rg},
  year         = 1999,
  journal      = {c't Magazin f\"{u}r Computer Technik},
  number       = 25,
  pages        = 252,
  url          = {http://www.heise.de/ct/ftp/99/25/252/}
}
@misc{Michael:2007,
  title        = {phonet.c},
  author       = {Michael, J{\"{o}}rg},
  year         = 2007,
  month        = aug,
  url          = {ftp://ftp.heise.de/pub/ct/listings/phonet.zip}
}
@book{Minkowski:1910,
  title        = {Geometrie der Zahlen},
  author       = {Minkowski, Hermann},
  year         = 1910,
  publisher    = {R. G. Teubner},
  address      = {Leipzig},
  url          = {https://archive.org/stream/geometriederzahl00minkrich}
}
@misc{Mokotoff:1997,
  title        = {Soundexing and Genealogy},
  author       = {Mokotoff, Gary},
  year         = 1997,
  url          = {http://www.avotaynu.com/soundex.htm},
  organization = {Avotaynu}
}
@inproceedings{Monge:1996,
  title        = {The Field Matching Problem: Algorithms and Applications},
  author       = {Monge, {Alvaro E.} and Elkan, {Charles P.}},
  year         = 1996,
  booktitle    = {Proceedings of the Second International Conference on Knowledge Discovery and Data Mining},
  location     = {Portland, Oregon},
  publisher    = {AAAI Press},
  series       = {KDD'96},
  pages        = {267--270},
  url          = {http://dl.acm.org/citation.cfm?id=3001460.3001516},
  acmid        = 3001516,
  numpages     = 4
}
@book{Moore:1977,
  title        = {Accessing Individual Records from Personal Data Files Using Non-Unique Identifiers},
  author       = {Moore, {Gwendolyn B.} and Kuhns, {John L.} and Trefftzs, {Jeffrey L.} and Montgomery, {Christine A.}},
  year         = 1977,
  month        = feb,
  publisher    = {National Bureau of Standards},
  address      = {Washington, D.C.},
  series       = {Special Publication},
  number       = {500-2},
  url          = {https://archive.org/details/accessingindivid00moor}
}
@inproceedings{Moreau:2008,
  title        = {Robust Similarity Measures for Named Entities Matching},
  author       = {Moreau, Erwan and Yvon, Fran\c{c}ois and Capp\'{e}, Olivier},
  year         = 2008,
  month        = aug,
  booktitle    = {COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1},
  pages        = {593--600}
}
@incollection{Morisita:1959,
  title        = {Measuring of interspecific association and similarity between communities},
  author       = {Morisita, Masaaki},
  year         = 1959,
  journal      = {Researches on Population Ecology},
  booktitle    = {Memoirs of the Faculty of Science},
  publisher    = {Kyushu University},
  series       = {Series E (Biology)},
  volume       = 3,
  pages        = {65--80}
}
@phdthesis{Morris:2012,
  title        = {A Quantitative MethoMethod for Vetting "Dark Network" Intelligence Sources for Social Network Analysis},
  author       = {Morris, {James F.}},
  year         = 2012,
  url          = {https://apps.dtic.mil/dtic/tr/fulltext/u2/a561702.pdf},
  school       = {Air Force Institute of Technology}
}
@inproceedings{Mosquera:2012,
  title        = {Towards Facilitating the Accessibility of Web 2.0 {T}exts through Text Normalisation},
  author       = {Mosquera, Alejandro and Lloret, Elena and Moreda, Paloma},
  year         = 2012,
  booktitle    = {Proceedings of the LREC workshop: Natural Language Processing for Improving Textual Accessibility (NLP4ITA) ; Istanbul, Turkey.},
  pages        = {9--14},
  url          = {http://www.taln.upf.edu/pages/nlp4ita/pdfs/mosquera-nlp4ita2012.pdf}
}
@article{Motyka:1950,
  title        = {Wst\c{c}pne badania nad lakami paludniowo-wschodnilj Lubel-szczyzny (Preliminary studies on meadows in the south-east of the province Lublin)},
  author       = {Motyka, {J.} and Dobrza\'{n}ski, {B.} and Zawadzki, {S.}},
  year         = 1950,
  journal      = {Annales Universitatis Mariae Curie-Sk\l{}odowska, Sectio E},
  volume       = 5,
  number       = 13,
  pages        = {367--447}
}
@inproceedings{Mountford:1962,
  title        = {An Index of Similarity and Its Application to Classificatory Problems},
  author       = {Mountford, {M. D.}},
  year         = 1962,
  month        = jul,
  booktitle    = {Progress in Soil Zoology: Papers from a Colloquium on Research Methods Organized by the Soil Zoology Committee of the International Society of Soil Science},
  publisher    = {Butterworths},
  address      = {London},
  pages        = {43--50},
  url          = {https://openlibrary.org/books/OL5908681M/Progress\_in\_soil\_zoology},
  editor       = {Murphy, {P. W.}}
}
@article{Mozley:1936,
  title        = {The Statistical Analysis of the Distribution of Pond Molluscs in Western {Canada}},
  author       = {Mozley, Alan},
  year         = 1936,
  journal      = {The American Naturalist},
  volume       = 70,
  number       = 728,
  doi          = {10.1086/280660}
}
@article{Munkres:1957,
  title        = {Algorithms for the Assignment and Transportation Problems},
  author       = {Munkres, James},
  year         = 1957,
  month        = mar,
  journal      = {Journal of the Society for Industrial and Applied Mathematics},
  volume       = 5,
  number       = 1,
  pages        = {32--38},
  doi          = {10.1137/0105003}
}
@inproceedings{Naseem:2011,
  title        = {Improved Similarity Measures For Software Clustering},
  author       = {Naseem, Rashid and Maqbool, Onaiza and Muhammad, Siraj},
  year         = 2011,
  month        = mar,
  booktitle    = {Proceedings of the Euromicro Conference on Software Maintenance and Reengineering, CSMR},
  doi          = {10.1109/CSMR.2011.9}
}
@article{Navarro:2001,
  title        = {A Guided Tour to Approximate String Matching},
  author       = {Navarro, Gonzalo},
  year         = 2001,
  month        = mar,
  journal      = {ACM Computing Surveys},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 33,
  number       = 1,
  pages        = {31--88},
  doi          = {10.1145/375360.375365},
  issn         = {0360-0300},
  acmid        = 375365,
  issue_date   = {March 2001},
  keywords     = {Levenshtein distance, edit distance, online string matching, text searching allowing errors},
  numpages     = 58
}
@article{Needleman:1970,
  title        = {A general method applicable to the search for similarities in the amino acid sequence of two proteins},
  author       = {Needleman, {Saul B.} and Wunsch, {Christian D.}},
  year         = 1970,
  journal      = {Journal of Molecular Biology},
  volume       = 48,
  number       = 3,
  pages        = {443--453},
  doi          = {10.1016/0022-2836(70)90057-4},
  issn         = {0022-2836},
  url          = {http://www.sciencedirect.com/science/article/pii/0022283670900574}
}
@article{Ochiai:1957,
  title        = {Zoogeographical studies on the soleoid fishes found in {Japan} and its neighhouring regions-II},
  author       = {Ochiai, Akira},
  year         = 1957,
  journal      = {Bulletin of the Japanese Society of Scientific Fisheries},
  volume       = 22,
  number       = 9,
  pages        = {526--530},
  doi          = {10.2331/suisan.22.526},
  url          = {https://www.jstage.jst.go.jp/article/suisan1932/22/9/22\_9\_526/\_pdf/-char/en}
}
@inproceedings{On:2007,
  title        = {Group Linkage},
  author       = {On, {Byung Won} and Koudas, Nick and Lee, Dongwon and Srivastava, Divesh},
  year         = 2007,
  booktitle    = {23rd International Conference on Data Engineering, ICDE 2007},
  address      = {Istanbul, Turkey},
  pages        = {496--505},
  doi          = {10.1109/ICDE.2007.367895}
}
@misc{OpenRefine:2012,
  title        = {Clustering In Depth},
  author       = {OpenRefine},
  year         = 2012,
  url          = {https://github.com/OpenRefine/OpenRefine/wiki/Clustering-In-Depth},
  organization = {OpenRefine}
}
@article{Orloci:1967,
  title        = {An Agllomerative Method for Classification of Plant Communities},
  author       = {Orl{\'{o}}ci, Laszlo},
  year         = 1967,
  month        = mar,
  journal      = {The Journal of Ecology},
  volume       = 55,
  number       = 1,
  pages        = {193--206},
  doi          = {10.2307/2257725}
}
@article{Otsuka:1936,
  title        = {The faunal character of the {Japan}ese Pleistocene marine Mollusca, as evidence of the climate having become colder during the Pleistocene in {Japan}},
  author       = {Otsuka, Yanosuke},
  year         = 1936,
  journal      = {Bulletin of the Biogeographical Society of Japan},
  volume       = 6,
  number       = 16,
  pages        = {165--170}
}
@misc{Ozbay:2015,
  title        = {Ozbay metric},
  author       = {Ozbay, Hakan},
  year         = 2015,
  url          = {https://github.com/hakanozbay/ozbay-metric}
}
@inproceedings{Paice:1990,
  title        = {Another stemmer},
  author       = {Paice, {Chris D.}},
  year         = 1990,
  month        = {Fall},
  booktitle    = {ACM SIGIR Forum},
  volume       = 24,
  number       = 3,
  pages        = {56--61},
  doi          = {10.1145/101306.101310.},
  url          = {https://dl.acm.org/citation.cfm?id=101310}
}
@inproceedings{Papineni:2002,
  title        = {BLEU: A Method for Automatic Evaluation of Machine Translation},
  author       = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, {Wei-Jing}},
  year         = 2002,
  booktitle    = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, July 2002},
  pages        = {311--318},
  url          = {https://www.aclweb.org/anthology/P02-1040.pdf}
}
@article{Parmar:2014,
  title        = {Study Existing Various Phonetic Algorithms and Designing and Development of a working model for the New Developed Algorithm and Comparison by implementing ti with Existing Algorithm(s)},
  author       = {Parmar, {Vimal P.} and Kumbharana, {CK}},
  year         = 2014,
  journal      = {International Journal of Computer Applications},
  volume       = 98,
  number       = 19,
  pages        = {45--49},
  doi          = {10.5120/17295-7795}
}
@inproceedings{Passonneau:2006,
  title        = {Measuring Agreement on Set-valued Items (MASI) for Semantic and Pragmatic Annotation},
  author       = {Passonneau, Rebecca},
  year         = 2006,
  month        = may,
  booktitle    = {Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC'06)},
  pages        = {831--836}
}
@article{Pearson:1900,
  title        = {Mathematical contributions to the theory of evolution. VII. On the correlation of characters not quantitatively measurable},
  author       = {Pearson, Karl},
  year         = 1900,
  journal      = {Philosophical Transactions of the Royal Society},
  volume       = {195 A},
  pages        = {1--47},
  doi          = {10.1098/rsta.1900.0022}
}
@article{Pearson:1913,
  title        = {On Theories of Association},
  author       = {Pearson, Karl and Heron, David},
  year         = 1913,
  journal      = {Biometrika},
  volume       = 9,
  number       = {1/2},
  pages        = {159--315},
  doi          = {10.2307/2331805}
}
@article{Pecina:2010,
  title        = {Lexical association measures and collocation extraction},
  author       = {Pecina, Pavel},
  year         = 2010,
  journal      = {Language Resources \& Evaluation},
  volume       = 44,
  number       = {1/2},
  pages        = {137--158},
  doi          = {10.2307/40666353}
}
@article{Peirce:1884,
  title        = {The Numerical Measure of the Success of Predictions},
  author       = {Peirce, {Charles S.}},
  year         = 1884,
  journal      = {Science},
  volume       = 4,
  number       = 93,
  pages        = {453--454},
  doi          = {10.1126/science.ns-4.93.453-a}
}
@article{Penrose:1952,
  title        = {Distance, Size and Shape},
  author       = {Penrose, {Lionel S.}},
  year         = 1952,
  month        = jan,
  journal      = {Annals of Eugenics},
  volume       = 17,
  number       = 1,
  pages        = {337--343},
  doi          = {10.1111/j.1469-1809.1952.tb02527.x}
}
@misc{Pfeifer:2000,
  title        = {WAIT 1.8 - soundex.c},
  author       = {Pfeifer, Ulrich},
  year         = 2000,
  url          = {https://fastapi.metacpan.org/source/ULPFR/WAIT-1.800/soundex.c}
}
@misc{Philips:1990,
  title        = {Metaphone},
  author       = {Philips, Lawrence},
  year         = 1990,
  month        = dec,
  url          = {http://aspell.net/metaphone/metaphone.basic}
}
@article{Philips:1990b,
  title        = {Hanging on the Metaphone},
  author       = {Philips, Lawrence},
  year         = 1990,
  month        = dec,
  journal      = {Computer Language},
  volume       = 7,
  number       = 12,
  pages        = {39--44}
}
@article{Philips:2000,
  title        = {The Double Metaphone Search Algorithm},
  author       = {Philips, Lawrence},
  year         = 2000,
  month        = jun,
  journal      = {C/C++ Users Journal},
  volume       = 18,
  number       = 6,
  pages        = {38--43}
}
@misc{Plique:2018,
  title        = {Talisman},
  author       = {Plique, Guillaume},
  year         = 2018,
  url          = {https://github.com/Yomguithereal/talisman}
}
@article{Pollock:1984,
  title        = {Automatic Spelling Correction in Scientific and Scholarly Text},
  author       = {Pollock, {Joseph J.} and Zamora, Antonio},
  year         = 1984,
  month        = apr,
  journal      = {Communications of the ACM},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 27,
  number       = 4,
  pages        = {358--368},
  doi          = {10.1145/358027.358048},
  issn         = {0001-0782},
  url          = {http://dl.acm.org/citation.cfm?id=358048},
  acmid        = 358048,
  issue_date   = {April 1984},
  keywords     = {dictionary lookup, similarity keys, spelling correction},
  numpages     = 11
}
@article{Porter:1980,
  title        = {An algorithm for suffix stripping},
  author       = {Porter, {Martin F.}},
  year         = 1980,
  month        = jul,
  journal      = {Program},
  volume       = 14,
  number       = 3,
  pages        = {130--137},
  doi          = {10.1108/eb046814},
  url          = {http://snowball.tartarus.org/algorithms/porter/stemmer.html}
}
@misc{Porter:2002,
  title        = {The English (Porter2) stemming algorithm},
  author       = {Porter, {Martin F.}},
  year         = 2002,
  month        = sep,
  url          = {http://snowball.tartarus.org/algorithms/english/stemmer.html}
}
@article{Postel:1969,
  title        = {Die K{\"{o}}lner Phonetik: Ein Verfahren zur Identifizierung von Personennamen auf der Grundlage der Gestaltanalyse},
  author       = {Postel, {Hans Joachim}},
  year         = 1969,
  journal      = {IBM-Nachrichten},
  volume       = 19,
  pages        = {925--931}
}
@misc{Prante:2015,
  title        = {elasticsearch -- HaasePhonetik.java},
  author       = {Prante, J{\"{o}}rg},
  year         = 2015,
  url          = {https://github.com/elastic/elasticsearch/blob/master/plugins/analysis-phonetic/src/main/java/org/elasticsearch/index/analysis/phonetic/HaasePhonetik.java}
}
@techreport{Radev:2001,
  title        = {Evaluation of Text Summarization in a Cross-lingual Information Retrieval Framework},
  author       = {Radev, Dragomir and Teufel, Simone and Saggion, Horacio and Lam, Wai and Blitzer, John and \c{C}elebi, Arda and Qi, Hong and Drabek, Elliott and Liu, Danyu},
  year         = 2001,
  url          = {https://pdfs.semanticscholar.org/44a1/df62a1c815fc84aa42788283655a38c85550.pdf},
  institution  = {Johns Hopkins}
}
@article{Raissouli:2009,
  title        = {Arithmetic-Geometric-Harmonic Mean of Three Positive Operators},
  author       = {Ra{\"{i}}ssouli, Mustapha and Leazizi,Fatima and Chergui, Mohamed},
  year         = 2009,
  journal      = {Journal of Inequalities in Pure and Applied Mathematics},
  volume       = 10,
  number       = 4,
  url          = {http://www.emis.de/journals/JIPAM/images/014\_08\_JIPAM/014\_08.pdf}
}
@article{Rand:1971,
  title        = {Objective Criteria for the Evaluation of Clustering Methods},
  author       = {Rand, {William M.}},
  year         = 1971,
  month        = dec,
  journal      = {Journal of the American Statistical Association},
  volume       = 66,
  number       = 336,
  pages        = {846--850},
  doi          = {10.2307/2284239}
}
@article{Ratcliff:1988,
  title        = {Pattern Matching: the Gestalt Approach},
  author       = {Ratcliff, {John W.} and Metzener, {David E.}},
  year         = 1988,
  journal      = {Dr. Dobbs Journal},
  url          = {http://www.drdobbs.com/database/pattern-matching-the-gestalt-approach/184407970}
}
@article{Raup:1979,
  title        = {Measurement of Faunal Similarity in Paleontology},
  author       = {Raup, {David M.} and Crick, {Rex E.}},
  year         = 1979,
  month        = sep,
  journal      = {Journal of Paleontology},
  volume       = 53,
  number       = 5,
  pages        = {1213--1227},
  doi          = {10.2307/1304099}
}
@misc{Rees:2013,
  title        = {The MDLD (Modified Damerau-Levenshtein Distance) Algorithm},
  author       = {Rees, Tony and Boehmer, Barbara},
  year         = 2013,
  month        = nov,
  url          = {https://confluence.csiro.au/public/taxamatch/the-mdld-modified-damerau-levenshtein-distance-algorithm}
}
@article{Rees:2014,
  title        = {Taxamatch, an Algorithm for Near ('Fuzzy') Matching on Scientific Names in Taxonomic Databases},
  author       = {Rees, Tony},
  year         = 2014,
  month        = sep,
  journal      = {PLoS ONE},
  volume       = 9,
  number       = 9,
  pages        = {1--27},
  doi          = {10.1371/journal.pone.0107510}
}
@misc{Repici:2013,
  title        = {Understanding Classic SoundEx Algorithms},
  author       = {Repici, {Dominic John}},
  year         = 2013,
  url          = {http://creativyst.com/Doc/Articles/SoundEx1/SoundEx1.htm\#SoundExAndCensus},
  organization = {Crativyst}
}
@techreport{Reth:1977,
  title        = {Eine Zugriffsmethode f{\"{u}}r die phonetische {\"{A}}hnlichkeitssuche},
  author       = {{von Reth}, Hans-Peter and Schek, Hans-J{\"{o}}rg},
  year         = 1977,
  series       = {Heidelberg Scientific Center technical reports},
  number       = {77.03.002},
  institution  = {IBM Deutschland GmbH.}
}
@inproceedings{Ring:2009,
  title        = {Finding `Lucy in Disguise': The Misheard Lyric Matching Problem},
  author       = {Ring, Nicholas and Uitdenbogerd, {Alexandra L.}},
  year         = 2009,
  booktitle    = {Information Retrieval Technology},
  publisher    = {Springer Berlin Heidelberg},
  address      = {Berlin, Heidelberg},
  pages        = {157--167},
  doi          = {10.1007/978-3-642-04769-5\_14},
  isbn         = {978-3-642-04769-5},
  editor       = {Lee, {Gary Geunbae} and Song, Dawei and Lin, Chin-Yew and Aizawa, Akiko and Kuriyama, Kazuko and Yoshioka, Masaharu and Sakai, Tetsuya}
}
@article{Roberts:1986,
  title        = {Ordination on the basis of fuzzy set theory},
  author       = {Roberts, {David W.}},
  year         = 1986,
  journal      = {Vegetatio},
  volume       = 66,
  number       = 3,
  pages        = {123--131},
  doi          = {10.1007/BF00039905}
}
@article{Robinson:1951,
  title        = {A Method for Chronologically Ordering Archaeological Deposits},
  author       = {Robinson, {W. S.}},
  year         = 1951,
  month        = apr,
  journal      = {American Antiquity},
  volume       = 16,
  number       = 4,
  pages        = {293--301},
  doi          = {10.2307/276978}
}
@inproceedings{Robinson:1967,
  title        = {Results of a prototype television bandwidth compression scheme},
  author       = {Robinson, {A. H.} and Cherry, Colin},
  year         = 1967,
  booktitle    = {Proceedings of the IEEE},
  volume       = 55,
  number       = 3,
  pages        = {356--364},
  doi          = {10.1109/PROC.1967.5493},
  organization = {IEEE}
}
@article{Rogers:1960,
  title        = {A Computer Program for Classifying Plants},
  author       = {Rogers, {David J.} and Tanimoto, {Taffee T.}},
  year         = 1960,
  month        = oct,
  journal      = {Science},
  volume       = 132,
  number       = 3434,
  pages        = {1115--1118},
  doi          = {10.1126/science.132.3434.1115}
}
@article{Rogot:1966,
  title        = {A proposed index for measuring agreement in test-retest studies},
  author       = {Rogot, Eugene and Goldberg, {Irving D.}},
  year         = 1966,
  journal      = {Journal of Chronic Diseases},
  doi          = {10.1016/0021-9681(66)90032-4}
}
@misc{rosettacode:2018,
  title        = {Run-length encoding},
  author       = {Rosetta Code},
  year         = 2018,
  url          = {https://rosettacode.org/wiki/Run-length\_encoding\#Python}
}
@misc{rosettacode:2018b,
  title        = {Longest common subsequence},
  author       = {Rosetta Code},
  year         = 2018,
  url          = {http://rosettacode.org/wiki/Longest\_common\_subsequence\#Dynamic\_Programming\_6}
}
@inproceedings{Ruibin:2005,
  title        = {An Adaptive Model for Phonetic String Search},
  author       = {Ruibin, Gong and Yun, {Chan Kai}},
  year         = 2005,
  booktitle    = {Knowledge-Based Intelligent Information and Engineering Systems, 9th International Conference, KES 2005 Melbourne, Australia, September 14-16, 2005 Proceedings, Part III},
  series       = {Lecture Notes in Artificial Intelligence},
  volume       = 3683,
  pages        = {915--921}
}
@misc{Rukasz:2018,
  title        = {PPRL -- Privacy Preserving Record Linkage},
  author       = {Rukasz, Dorothea},
  year         = 2018,
  url          = {https://github.com/cran/PPRL}
}
@inproceedings{Russ:2014,
  title        = {Computer-Based Coding of Occupation Codes for Epidemiological Analysis},
  author       = {Russ, {Daniel E.} and Ho, Kwan-Yuet and Johnson, {Calvin A.} and Friesen, {Melissa C.}},
  year         = 2014,
  booktitle    = {2014 IEEE 27th International Symposium on Computer-Based Medical Systems},
  pages        = {347--350},
  doi          = {10.1109/CBMS.2014.79}
}
@misc{Russell:1917,
  title        = {Index},
  author       = {Russell, {Robert C.}},
  year         = 1918,
  number       = 1261167,
  url          = {https://patentimages.storage.googleapis.com/31/35/a1/f697a3ab85ced6/US1261167.pdf},
  nationality  = {US},
  yearfiled    = 1917
}
@article{Russell:1940,
  title        = {On Habitat and Association of Species of Anopheline Larvae in South-Eastern Madras},
  author       = {Russell, {Paul F.} and Rao, {T. Ramachandra}},
  year         = 1940,
  journal      = {Journal of the Malaria Institute of India},
  volume       = 3,
  number       = 1,
  pages        = {153--178}
}
@article{Ruzicka:1958,
  title        = {Anwendung mathematische-statistischer Methoden in der Geobotanik (Synthetische Bearbeitung von Aufnahmen)},
  author       = {R\r{u}{\v{z}}i{\v{c}}ka, M.},
  year         = 1958,
  journal      = {Biologia, Bratislava},
  volume       = 13,
  pages        = {647--661}
}
@misc{Savoy:2005,
  title        = {{IR} Multilingual Resources at UniNE},
  author       = {Savoy, Jacques},
  year         = 2005,
  address      = {Neuchatel},
  url          = {http://members.unine.ch/jacques.savoy/clef/},
  organization = {University of Neuchatel}
}
@article{Schinke:1996,
  title        = {A Stemming Algorithm for Latin Text Databases},
  author       = {Schinke, Robyn and Greengrass, Mark and Robertson, {Alexander M.} and Willett, Peter},
  year         = 1996,
  journal      = {Journal of Documentation},
  volume       = 52,
  number       = 2,
  pages        = {172--187},
  doi          = {10.1108/eb026966}
}
@article{Schnell:2004,
  title        = {A Toolbox for record linkage},
  author       = {Schnell, Rainer and Bachteler, Tobias and Bender, Stefan},
  year         = 2004,
  journal      = {Australian Journal of Statistics},
  volume       = 33,
  number       = {1-2},
  pages        = {125--133},
  url          = {https://pdfs.semanticscholar.org/2353/21c24ed0401cd05d7752c2c8a8da5b7a4dc0.pdf}
}
@article{Schurer:2007,
  title        = {Creating a nationally representative individual and household sample for Great Britain, 1851 to 1901 - The Victorian Panel Study (VPS)},
  author       = {Sch\"{u}rer, Kevin},
  year         = 2007,
  journal      = {Historical Social Research / Historische Sozialforschung},
  volume       = 32,
  number       = 2,
  pages        = {211--331},
  doi          = {10.2307/20762213}
}
@article{Scott:1955,
  title        = {Reliability of Content Analysis: The Case of Nominal Scale Coding},
  author       = {Scott, {William A.}},
  year         = 1955,
  journal      = {Public Opinion Quarterly},
  volume       = 19,
  number       = 3,
  pages        = {321--325},
  doi          = {10.1086/266577}
}
@article{Seiffert:1993,
  title        = {Problem 887},
  author       = {Seiffert, Heinz-J{\"{u}}rgen},
  year         = 1993,
  journal      = {Nieuw Archief voor Wiskunde},
  volume       = 11,
  number       = 4,
  pages        = 176
}
@misc{SequentiX:2018,
  title        = {Distance Measures},
  author       = {SequentiX},
  year         = 2018,
  url          = {https://www.sequentix.de/gelquest/help/distance\_measures.htm}
}
@article{Shannaq:2010,
  title        = {Using Product Similarity for Adding Business},
  author       = {Shannaq, {Boumedyen A. N.} and Alexandrov, {Victor V.}},
  year         = 2010,
  month        = oct,
  journal      = {Global Journal of Computer Science and Technology},
  volume       = 10,
  number       = 12,
  pages        = {2--8},
  url          = {https://www.sial.iias.spb.su/files/386-386-1-PB.pdf}
}
@article{Shapira:2007,
  title        = {Edit distance with move operations},
  author       = {Shapira, Dana and Storer, {James A.}},
  year         = 2007,
  month        = jun,
  journal      = {Journal of Discrete Algorithms},
  volume       = 5,
  number       = 2,
  pages        = {380--392},
  doi          = {10.1016/j.jda.2005.01.010}
}
@article{Shi:1993,
  title        = {Multivariate data analysis in palaeoecology and palaeobiogeography---a review},
  author       = {Shi, {Guang R.}},
  year         = 1993,
  journal      = {Palaeogeography, Palaeoclimatology, Palaeoecology},
  volume       = 105,
  number       = {3-4},
  pages        = {199--234},
  doi          = {10.1016/0031-0182(93)90084-v}
}
@article{Sidorov:2014,
  title        = {Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model},
  author       = {Sidorov, Grigori and Gelbukh, Alexander and G{\'{o}}mez-Adorno, Helena and Pinto, David},
  year         = 2014,
  journal      = {Computaci\'{o}n y Sistemas},
  volume       = 18,
  number       = 3,
  doi          = {10.13053/CyS-18-3-2043},
  url          = {http://www.scielo.org.mx/pdf/cys/v18n3/v18n3a7.pdf}
}
@article{Simpson:1949,
  title        = {Measurement of Diversity},
  author       = {Simpson, {Edward H.}},
  year         = 1949,
  month        = apr,
  journal      = {Nature},
  volume       = 163,
  pages        = 688,
  doi          = {10.1038/163688a0},
  url          = {https://www.nature.com/articles/163688a0}
}
@misc{Sjoo:2009,
  title        = {SwamiSfinxBix},
  author       = {Sj{\"{o}}{\"{o}}, Allan},
  year         = 2009,
  address      = {Uppsala},
  url          = {http://www.swami.se/download/18.248ad5af12aa8136533800093/swamiSfinxBis.java.txt},
  organization = {Uppsala universitet}
}
@article{Smith:1981,
  title        = {Identification of common molecular subsequences},
  author       = {Smith, {Temple F.} and Waterman, {Michael S.}},
  year         = 1981,
  journal      = {Journal of Molecular Biology},
  volume       = 147,
  number       = 1,
  pages        = {195--197},
  doi          = {10.1016/0022-2836(81)90087-5},
  issn         = {0022-2836},
  url          = {http://www.sciencedirect.com/science/article/pii/0022283681900875}
}
@article{Snae:2002,
  title        = {An Interface for Mining Genealogical Nominal Data Using the Concept of linkage and a Hybrid Name Matching Algorithm},
  author       = {Snae, Chakkrit and Diaz, Bernard},
  year         = 2002,
  journal      = {Journal of 3D-Forum Society},
  volume       = 16,
  number       = 1,
  pages        = {142--147},
  url          = {https://web.archive.org/web/20050329140715/www.csc.liv.ac.uk/~chakkrit/Publications/hc2001\_Journal.pdf}
}
@article{Sokal:1958,
  title        = {A Statistical Method for Evaluating Systematic Relationships},
  author       = {Sokal, {Robert R.} and Michener, {Charles D.}},
  year         = 1958,
  month        = mar,
  journal      = {The University of Kansas Science Bulletin},
  volume       = {38, part 2},
  number       = 22,
  pages        = {1409--1438},
  url          = {https://archive.org/details/cbarchive\_133648\_astatisticalmethodforevaluatin1902}
}
@book{Sokal:1963,
  title        = {Principles of Numerical Taxonomy},
  author       = {Sokal, {Robert R.} and Sneath, {Peter H. A.}},
  year         = 1963,
  publisher    = {W. H. Freeman and Company},
  address      = {San Francisco}
}
@inproceedings{Somers:1998,
  title        = {Similarity Metrics for AliAlign Children's Articulation Data},
  author       = {Somers, {Harold L.}},
  year         = 1998,
  booktitle    = {ACL '98/COLING '98 Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 2},
  pages        = {1227--1232},
  doi          = {10.3115/980691.980769}
}
@misc{Song:2011,
  title        = {Typo-Distance},
  author       = {Song, Wayne},
  year         = 2011,
  url          = {https://github.com/wsong/Typo-Distance}
}
@article{Sorensen:1948,
  title        = {A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on Danish commons},
  author       = {S{\o}rensen, Thorvald},
  year         = 1948,
  journal      = {Kongelige Danske Videnskabernes Selskab},
  volume       = 5,
  number       = 4,
  pages        = {1--34},
  url          = {http://www.royalacademy.dk/Publications/High/295\_S\%C3\%B8rensen,\%20Thorvald.pdf}
}
@book{Sorgenfrei:1958,
  title        = {Molluscan Assemblages from the Marine Middle Miocene of South Jutland and Their Environments},
  author       = {Sorgenfrei, Theodor},
  year         = 1958,
  publisher    = {Danmarks Geologiske Unders\o{}gelse},
  address      = {1--503},
  series       = 2,
  number       = 79
}
@article{Steffensen:1934,
  title        = {On Certain Measures of Dependence Between Statistical Variables},
  author       = {Steffensen, {J. F.}},
  year         = 1934,
  month        = may,
  journal      = {Biometrika},
  volume       = 26,
  number       = {1/2},
  pages        = {251--255},
  doi          = {10.2307/2332058}
}
@techreport{Steingold:2015,
  title        = {An Information Theoretic Metric for Multi-Class Categorization},
  author       = {Steingold, Sam and Laclav{\'{i}}k, Michal},
  year         = 2015,
  url          = {https://github.com/Magnetic/proficiency-metric/blob/master/paper/predeval.pdf},
  institution  = {Magnetic Media Online}
}
@misc{Stern:2014,
  title        = {DamerauLevenshteinAlgorithm.java},
  author       = {Stern, {Kevin L.}},
  year         = 2014,
  url          = {https://github.com/KevinStern/software-and-algorithms/blob/master/src/main/java/blogspot/software\_and\_algorithms/stern\_library/string/DamerauLevenshteinAlgorithm.java}
}
@article{Stiles:1961,
  title        = {The Association Factor in Information Retrieval},
  author       = {Stiles, {H. Edmund}},
  year         = 1961,
  month        = apr,
  journal      = {Journal of the ACM},
  volume       = 8,
  number       = 2,
  pages        = {271--279},
  doi          = {10.1145/321062.321074}
}
@inproceedings{Stoilos:2005,
  title        = {A String Metric for Ontology Alignment},
  author       = {Stoilos, Giorgos and Stamou, Giorgos and Kollias, Stefanos},
  year         = 2005,
  month        = nov,
  booktitle    = {ISWC'05 Proceedings of the 4th international conference on The Semantic Web},
  address      = {Galway, Ireland},
  pages        = {624--637},
  doi          = {10.1007/11574620\_45}
}
@article{Stuart:1953,
  title        = {The Estimation and Comparison of Strengths of Association in Contingency Tables},
  author       = {Stuart, A.},
  year         = 1953,
  month        = jun,
  journal      = {Biometrika},
  volume       = 40,
  number       = {1/2},
  pages        = {105--110},
  doi          = {10.2307/2333101}
}
@article{Szymkiewicz:1934,
  title        = {Une contribution statistique {\`{a}} la g{\'{e}}ographie floristique},
  author       = {Szymkiewicz, Dezydery},
  year         = 1934,
  journal      = {Acta Societatis Botanicorum Poloniae},
  volume       = 11,
  number       = 3,
  pages        = {249--265},
  doi          = {10.5586/asbp.1934.012},
  url          = {https://pbsociety.org.pl/journals/index.php/asbp/article/download/asbp.1934.012/6710}
}
@book{Taft:1970,
  title        = {Name Search Techniques},
  author       = {Taft, {Robert L.}},
  year         = 1970,
  publisher    = {Bureau of Systems Development, New York State Identification and Intelligence System},
  series       = {Special report (New York State Identification and Intelligence System)},
  lccn         = 76635950
}
@techreport{Tanimoto:1958,
  title        = {An Elementary Mathematical theory of Classification and Prediction},
  author       = {Tanimoto, {T. T.}},
  year         = 1958,
  institution  = {IBM}
}
@article{Tarwid:1960,
  title        = {Szacowanie zbieznosci nisz ekologicznych gatunkow droga oceny prawdopodobienstwa spotykania sie ich w polowach},
  author       = {Tarwid, Kazimierz},
  year         = 1960,
  journal      = {Ekologia Polska, Seria B},
  number       = 6,
  pages        = {115--130}
}
@article{Tichy:1984,
  title        = {The String-to-String Correction Problem with Block Moves},
  author       = {Tichy, {Walter F.}},
  year         = 1984,
  month        = nov,
  journal      = {ACM Transactions on Computer Systems},
  volume       = 2,
  number       = 4,
  pages        = {309--321},
  doi          = {10.1145/357401.357404}
}
@misc{Ticki:2016,
  title        = {Eudex: A blazingly fast phonetic reduction/hashing algorithm},
  author       = {Ticki},
  url          = {https://github.com/ticki/eudex}
}
@misc{Ticki:2016b,
  title        = {The Eudex Algorithm},
  author       = {Ticki},
  year         = 2016,
  month        = dec,
  url          = {http://ticki.github.io/blog/the-eudex-algorithm/}
}
@incollection{Tulloss:1997,
  title        = {Assessment of Similarity Indices for Undesirable Properties and a New Tripartite Similarity Index Based on Cost Functions},
  author       = {Tulloss, {Rodham E.}},
  year         = 1997,
  booktitle    = {Mycology in Sustainable Development: Expanding Concepts, Vanishing Borders},
  publisher    = {Parkway Publishers, Inc.},
  address      = {Boone, NC},
  pages        = {122--143},
  editor       = {Palm, {Mary E.} and Chapela, {Ignacio H.}}
}
@incollection{Turner:1988,
  title        = {Packaging Information for Peer Review: New Co-Word Analysis Techniques},
  author       = {Turner, {W. A.} and Charton, {G.} and Laville, {F.} and Michelet, {B.}},
  year         = 1988,
  booktitle    = {Handbook of Quantitative Studies of Science and Technology},
  publisher    = {New Holland}
}
@article{Tversky:1977,
  title        = {Features of Similarity},
  author       = {Tversky, Amos},
  year         = 1977,
  journal      = {Psychological Review},
  volume       = 84,
  number       = 4,
  pages        = {327--352},
  doi          = {10.1037/0033-295x.84.4.327},
  url          = {http://www.cogsci.ucsd.edu/~coulson/203/tversky-features.pdf}
}
@article{Ukkonen:1992,
  title        = {Approximate string-matching with q-grams and maximal matches},
  author       = {Ukkonen, Esko},
  year         = 1992,
  journal      = {Theoretical Computer Science},
  volume       = 92,
  number       = 1,
  pages        = {191--211},
  doi          = {10.1016/0304-3975(92)90143-4}
}
@article{Upholt:1977,
  title        = {Estimation of {DNA} sequence divergence from comparison of restriction endonuclease digests},
  author       = {Upholt, {William B.}},
  year         = 1977,
  month        = jan,
  journal      = {Nucleic Acids Research},
  volume       = 4,
  number       = 5,
  pages        = {1257--1265},
  doi          = {10.1093/nar/4.5.1257}
}
@book{US:1997,
  title        = {Using the Census Soundex},
  author       = {United States},
  year         = 1997,
  publisher    = {National Archives and Records Administration},
  address      = {Washington, D.C.},
  series       = {General Information Leaflet},
  number       = 55,
  url          = {https://hdl.handle.net/2027/pur1.32754067050041}
}
@misc{US:2007,
  title        = {Soundex System: The Soundex Indexing System},
  author       = {United States},
  year         = 2007,
  address      = {Washington, D.C.},
  url          = {https://www.archives.gov/research/census/soundex.html},
  organization = {National Archives and Records Administration}
}
@article{Varol:2012,
  title        = {Hybrid Matching Algorithm for Personal Names},
  author       = {Varol, Cihan and Bayrak, Coskun},
  year         = 2012,
  month        = sep,
  journal      = {Journal of Data and Information Quality},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 3,
  number       = 4,
  pages        = {8:1--8:18},
  doi          = {10.1145/2348828.2348830},
  issn         = {1936-1955},
  acmid        = 2348830,
  articleno    = 8,
  issue_date   = {September 2012},
  keywords     = {Data quality, edit-distance, information quality, phonetic strategy, spelling correction},
  numpages     = 18
}
@article{Wagner:1974,
  title        = {The String-to-String Correction Problem},
  author       = {Wagner, {Robert A.} and Fischer, {Michael J.}},
  year         = 1974,
  month        = jan,
  journal      = {Journal of the ACM},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  volume       = 21,
  number       = 1,
  pages        = {168--173},
  doi          = {10.1145/321796.321811},
  issn         = {0004-5411},
  acmid        = 321811,
  issue_date   = {Jan. 1974},
  numpages     = 6
}
@article{Wang:2014,
  title        = {Extending String Similarity Join to Tolerant Fuzzy Token Matching},
  author       = {Wang, Jiannan and Li, Guoliang and Feng, Jianhua},
  year         = 2014,
  journal      = {ACM Transactions on Database Systems},
  volume       = 39,
  number       = 1,
  pages        = {1--45},
  doi          = {10.1145/2535628}
}
@phdthesis{Warrens:2008,
  title        = {Similarity Coefficients for Binary Data: Properties of Coefficients, Coefficient Matrices, Multi-way Metrics and Multivariate Coefficients},
  author       = {Warrens, {Matthijs J.}},
  year         = 2008,
  month        = jun,
  journal      = {Psychometrika},
  address      = {Leiden},
  volume       = 73,
  number       = 3,
  pages        = {487--502},
  url          = {https://openaccess.leidenuniv.nl/bitstream/handle/1887/12987/Full\_thesis.pdf},
  school       = {Universiteit Leiden}
}
@techreport{Weitzman:1970,
  title        = {Measures of overlap of income distributions of white and Negro families in the United States},
  author       = {Weitzman, {Murray S.}},
  year         = 1970,
  address      = {Washington, D.C.},
  number       = 22,
  institution  = {U.S. Department of Commerce, Bureau of Census}
}
@misc{White:Nd,
  title        = {How to Strike a Match},
  author       = {White, Simon},
  year         = {Nd.},
  url          = {http://www.catalysoft.com/articles/StrikeAMatch.html},
  note         = {The oldest version on Internet Archive was archived in 2004.},
  howpublished = {Web}
}
@article{Whittaker:1952,
  title        = {A Study of Summer Foliage Insect Communities in the Great Smoky Mountains},
  author       = {Whittaker, {R. H.}},
  year         = 1952,
  month        = jan,
  journal      = {Ecological Monographs},
  volume       = 22,
  number       = 1,
  pages        = {1--44},
  doi          = {10.2307/1948527}
}
@book{Whittaker:1982,
  title        = {Ordination of Plant Communities},
  author       = {Whittaker, {Robert H.}},
  year         = 1982,
  publisher    = {Springer Netherlands},
  series       = {Handbook of Vegetation Sciecne},
  volume       = 5,
  number       = 2
}
@misc{Wikibooks:2018,
  title        = {Algorithm Implementation/Strings/Longest common substring},
  author       = {Wikibooks},
  year         = 2018,
  url          = {https://en.wikibooks.org/wiki/Algorithm\_Implementation/Strings/Longest\_common\_substring\#Python}
}
@article{Wilde:1988,
  title        = {Nicht w{\"{o}}rtlich genommen, 'Schreibweisentolerante' Suchroutine in dBASE implementiert},
  author       = {Georg, Wilde and Meyer, Carsten},
  year         = 1988,
  month        = oct,
  journal      = {c't Magazin f\"{u}r Computer Technik},
  number       = 10,
  pages        = {126--131}
}
@mastersthesis{Wilz:2005,
  title        = {Aspekte der Kodierung phonetischer {\"{A}}hnlichkeiten in deutschen Eigennamen},
  author       = {Wilz, Martin},
  year         = 2005,
  address      = {K\"{o}ln},
  url          = {http://ifl.phil-fak.uni-koeln.de/sites/linguistik/Phonetik/import/Phonetik\_Files/Allgemeine\_Dateien/Martin\_Wilz.pdf},
  school       = {Universit\"{a}t zu K\"{o}ln}
}
@techreport{Winkler:1990,
  title        = {String Comparator Metrics and Enhanced Decision Rules in the Fellegi-Sunter Model of Record Linkage},
  author       = {Winkler, {William E.}},
  year         = 1990,
  journal      = {Proceedings of the Section on Survey Research Methods},
  address      = {Washington, D.C.},
  url          = {https://files.eric.ed.gov/fulltext/ED325505.pdf},
  institution  = {U.S. Bureau of the Census, Statistical Research Division}
}
@misc{Winkler:1994,
  title        = {strcmp95.c},
  author       = {Winkler, {William E.} and McLaughlin, George and Jaro, {Matthew A.} and Lync, Maureen},
  year         = 1994,
  month        = jan,
  url          = {https://web.archive.org/web/20110629121242/http://www.census.gov/geo/msb/stand/strcmp.c}
}
@phdthesis{Xiang:2013,
  title        = {Similarity-based Virtual Screening: Effect of the Choice of Similarity Measure},
  author       = {Xiang, Hua},
  year         = 2013,
  url          = {http://etheses.whiterose.ac.uk/5662/1/Thesis\_Final.pdf},
  school       = {The University of Sheffield}
}
@misc{Yang:2016,
  title        = {New metrics for learning and inference on sets, ontologies, and functions},
  author       = {Yang, Ruiyu and Jiang, Yuxiang and Hahn, {Matthew W.} and Houseworth, {Elizabeth A.} and Radivojac, Predrag},
  year         = 2016,
  month        = mar,
  url          = {https://arxiv.org/abs/1603.06846v1}
}
@article{Yates:1934,
  title        = {Contingency Tables Involving Small Numbers and the \$\chi\$2~{T}est},
  author       = {Yates, Frank},
  year         = 1934,
  journal      = {Supplement to the Journal of the Royal Statistical Society},
  volume       = 1,
  number       = 2,
  pages        = {217--235},
  doi          = {10.2307/2983604}
}
@article{Youden:1950,
  title        = {Index for Rating Diagnostic Tests},
  author       = {Youden, {William John}},
  year         = 1950,
  journal      = {Cancer},
  volume       = 3,
  number       = 1,
  pages        = {32--35},
  doi          = {10.1002/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3}
}
@article{Yujian:2007,
  title        = {A Normalized Levenshtein Distance Metric},
  author       = {Yujian, Li and Bo, Liu},
  year         = 2007,
  journal      = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume       = 29,
  number       = 6,
  pages        = {1091--1095},
  doi          = {10.1109/TPAMI.2007.1078}
}
@article{Yule:1912,
  title        = {On the Methods of Measuring Association Between Two Attributes},
  author       = {Yule, {G. Udny}},
  year         = 1912,
  journal      = {Journal of the Royal Statistical Society},
  volume       = 75,
  number       = 6,
  doi          = {10.2307/2340126}
}
@book{Yule:1968,
  title        = {An Introduction to the Theory of Statistics},
  author       = {Yule, {G. Udny} and Kendall, {Maurice G.}},
  year         = 1968,
  publisher    = {Griffin},
  address      = {London},
  edition      = 14
}
@misc{Zackwehdex:2014,
  title        = {Super Fast and Accurate string distance algorithm: Sift4},
  author       = {Zackwehdex, Siderite},
  year         = 2014,
  url          = {https://siderite.blogspot.com/2014/11/super-fast-and-accurate-string-distance.html}
}
@misc{Zedlitz:2015,
  title        = {phonet4java Phonet.java},
  author       = {Zedlitz, Jesper},
  year         = 2015,
  url          = {https://github.com/jze/phonet4java/blob/master/src/main/java/de/zedlitz/phonet4java/Phonet.java}
}
@inproceedings{Zobel:1996,
  title        = {Phonetic String Matching: Lessons from Information Retrieval},
  author       = {Zobel, Justin and Dart, Philip},
  year         = 1996,
  booktitle    = {Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval},
  location     = {Zurich, Switzerland},
  publisher    = {ACM},
  address      = {New York, NY, USA},
  series       = {SIGIR '96},
  pages        = {166--172},
  doi          = {10.1145/243199.243258},
  isbn         = {0-89791-792-8},
  acmid        = 243258,
  numpages     = 7
}

@Comment{jabref-meta: databaseType:bibtex;}