1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
|
#
# template configuration file for Frog
#
# this file contains all necessary for the a deafult Frog setup
# along with comments on how/why
# Note: comments are added BEFORE the option they belong to
#
# The configuraration is separated in sections, labeled like [[this]]
# each section belonging to one of the Frog modules. The order is not important
# an frog can work with missing sections too
#
# First the UNLABELED gobal section
#
# version information of this config file (is not well maintained)
version=0.12
#
# the directory to store temporary files. You may change this in case
# of space problems in/tmp
tmpdir=/tmp/
#
# name of file describing a generic character filter to use on ALL input
# before any further processing. The default file maps different kind of
# quotes to a single quote: ‘’`´ ==> '
char_filter_file=frog.filter
# the Tagger section
[[tagger]]
#
# version information of this module
version=1.0
#
# name of the Mbt settingsfile defining the Tagger
settings="Frog.mbt.1.0.settings"
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-mbpos-cgn"
#
# the name of the subsets file. (CGN extension)
# subsets give a mapping from attributes to allowed value like:
# ntype = soort, eigen
# getal = ev, mv, getal
#
subsets_file="subsets.cgn"
#
# the name of the constraints file. (CGG extension)
# constrainst give a mapping from values to POS tags
constraints_file="constraints.cgn"
#
# the name of the token translation file
# token translations give a mapping from Ucto Tokens to CGN tags
# like
# PUNCTUATION LET()
# ABBREVIATION-KNOWN SPEC(afk)
# SMILEY SPEC(symb)
#
token_trans_file=cgn_token.trans
#
# set a debug value for this module. using --debug=T<value> might be handier
# debug=0
# the IOB chunker section
[[IOB]]
#
# version information of this module
version=2.0
#
# name of the Mbt settingsfile defining the Chunker
settings="chunkgen.data.settings"
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-chunker-nl"
#
# set a debug value for this module. using --debug=c<value> might be handier
debug=0
# the NER section
[[NER]]
#
# version information of this module
version=2.2
#
# name of the Mbt settingsfile defining the NER
settings="nergen.data.settings"
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-ner-nl"
#
# the name of the file with the names of the gazeteer files
# this is a list of categories + filenames, each file with gazeteer info for
# that category
# example:
# per voornamen.ner
# per familienamen.ner
# eve eve.ner
# loc loc.ner
# meaning 'per' tags are te be found in voornamen.ner
# which might look like this:
# Allerheiligen
# 1 april
# 5 mei
# Bevrijdingsdag
# Carnaval
# Dag van de Arbeid
# so multi_word entires are allowed
known_ners=ners.known
#
# maximum size of NE to handle
max_ner_size=15
#
# set a debug value for this module. using --debug=n<value> might be handier
#debug=8
# the lemmatizer section
[[mblem]]
#
# version information of this module
version=1.2
#
# the name of the trained Timbl datafile
treeFile=mblem.tree
#
# The Timbl options used for training
timblOpts="-a1 -w2"
#
# a list of CGN tags that will NOT be analyzed, but taken as-is
# so an abreviation like 'a.u.b.' with tag SPEC(afk) will get itself as lemma
one_one_tags=LET(),SPEC(symb),SPEC(deeleigen),SPEC(vreemd),SPEC(afk)
#
# a list of tokens to handle special based on Tokenizer results
token_strip_file=striptokens.txt
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-mblem-nl"
#
# set a debug value for this module. using --debug=l<value> might be handier
#debug=0
# the MWU section
[[mwu]]
#
# version information of this module
version=1.0
#
# the file with the list of known MWU's
t=Frog.mwu.1.0
#
# all words with this CGN tag will be seen as (part of) an MWU
gluetag=SPEC(deeleigen)
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-mwu-nl"
#
# set a debug value for this module. using --debug=m<value> might be handier
#debug=0
# the Morphological analyzer section
[[mbma]]
#
# version information of this module
version=1.0
#
# the name of the trained Timbl datafile
treeFile=mbma.igtree
#
# The Timbl options used for training
timblOpts="-a1 -w2"
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-mbma-nl"
#
# set a debug value for this module. using --debug=a<value> might be handier
#debug=0
# the Ucto tokenizer section
[[tokenizer]]
#
# the (default) tokenizer config file to use
rulesFile="tokconfig-nld"
#
# set a debug value for this module. using --debug=t<value> might be handier
#debug=0
# the parser section
[[parser]]
#
# version information of this module
version=1.0
#
# The trained Timbl for 'pairs' with the Timbl options
pairsFile=Frog.mbdp.1.0.pairs.sampled.ibase
pairsOptions="-a1 +D +G0 +vS+db+di"
#
# The trained Timbl for 'dir' with the Timbl options
dirFile=Frog.mbdp.1.0.dir.ibase
dirOptions="-a1 +D +G0 +vS+db+di"
#
# The trained Timbl for 'rels' with the Timbl options
relsFile=Frog.mbdp.1.0.rels.ibase
relsOptions=" -a1 +D +G0 +vS+db+di"
#
# the maximum depth for dependencies
maxDepSpan=20
#
# FoLiA setname to use when creating FoLiA
set="http://ilk.uvt.nl/folia/sets/frog-depparse-nl"
#
# the alpino server options (used by the --alpino=server option)
alpino_host=localhost
alpino_port=8004
|
