-
Notifications
You must be signed in to change notification settings - Fork 8
/
gle.tdl
398 lines (321 loc) · 12.6 KB
/
gle.tdl
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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
;;; -*- Mode: tdl; Coding: utf-8; -*-
;;;
;;; Copyright (c) 2000 -- 2013 Dan Flickinger ([email protected]);
;;; copyright (c) 2009 -- 2013 Stephan Oepen ([email protected]); (ERG)
;;; Copyright (c) 2014 -- NTU Computational Linguistics Lab; (Zhong)
;;; modified by Sanghoun Song ([email protected], 2014-11-24)
;;; see `LICENSE' for conditions.
;;;
;;;
;;; generic lexical entries, i.e. entries that are not activated directly by
;;; orthography. all generic entries are distinguished from native lexical
;;; entries by virtue of their [ ONSET unk_onset ]. generics are sub-divided
;;; into two sub-classes, named (somewhat unfortunately) `unknown' generics
;;; and `generic' generics (that is `unk' and `gen', respectively).
;;;
;;; the former are designed for unknown words and activated on the basis of
;;; PoS tags, the latter correspond to named entities that are recognized by
;;; string-level properties during chart mapping (the equivalent of what in
;;; the YY tradition used to be `ersatz' lexical entries). see the comments
;;; in `tmr.tdl' (token mapping) and `lfr.tdl' (lexical filtering) for further
;;; background.
;;;
;;; _fix_me_
;;; i believe nothing stands in our way of giving these entries a `meaningful'
;;; orthography now, e.g. something like "_generic_trans_verb_bse_", or so, for
;;; interactive testing (including the LKB).
;;;
;;; furthermore, i suspect we can now ditch the older `gle' entries, used for
;;; generation only, and instead use some of the entries below (those with a
;;; singleton RELS list, fully instantiated PRED, and underspecified CARG) in
;;; *generic-lexical-entries*. (22-jan-09; oe)
;;;
;;; SSH 2014-11-24: Generic Lexical Entries for Zhong
;;; The tagset used in the Stanford POS tagger for Chinese is CTB.
;;; The guideline is written by Fei Xia and downloadable below.
;;; http://www.cis.upenn.edu/~chinese/posguide.3rd.ch.pdf
;;; There are 33 tags.
; AD adverb 还
; AS aspect maker 着
; BA 把 in ba-construction 把，将
; CC coordinating conjunction 和
; CD cardinal number 一百
; CS subordinating conjunction 虽然
; DEC 的 in a relative-clause 的
; DEG associative 的的
; DER 得 in V-de const. and V-de-R 得
; DEV 地 before VP 地
; DT determiner 这
; ETC for words 等，等等 等，等等
; FW foreign words ＩＳＯ
; IJ interjection 啊
; JJ other noun-modifier 男，共同
; LB 被 in long bei-const 被，给
; LC localizer 里
; M measure word 个
; MSP other particle 所
; NN common noun 书
; NR proper noun 美国
; NT temporal noun 今天
; OD ordinal number 第一
; ON onomatopoeia 哈哈，哗哗
; P preposition excl. 被and把从
; PN pronoun 他
; PU punctuation ，、。
; SB 被 in short bei-const 被，给
; SP sentence-final particle 吗
; VA predicative adjective 红
; VC 是 是
; VE 有 as the main verb 有
; VV other verb 走
generic_name := proper-name-lex &
[ SYNSEM.LKEYS.KEYREL.CARG #carg,
STEM < "_generic_name_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "NR" >,
+CARG #carg ] > ].
generic_foreign-word := proper-name-lex &
[ SYNSEM.LKEYS.KEYREL.CARG #carg,
STEM < "_generic_fw_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "FW" >,
+CARG #carg ] > ].
generic_card := num-adj-lex &
[ SYNSEM.LKEYS.KEYREL.CARG #carg,
STEM < "_generic_card_ne_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "CD" >,
+CARG #carg ] > ].
generic_common-noun := count-noun-lex &
[ SYNSEM.LKEYS.KEYREL.PRED #pred,
STEM < "_generic_cn_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "NN" >,
+PRED #pred ] > ].
generic_temp-noun := time-noun-lex &
[ SYNSEM.LKEYS.KEYREL.PRED #pred,
STEM < "_generic_tn_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "NT" >,
+PRED #pred ] > ].
generic_classifier := classifier-lex &
[ SYNSEM.LKEYS.KEYREL.PRED cl_x_rel,
STEM < "_generic_cl_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "M" > ] > ].
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; SSH 2015-03-30: This causes a loopy error in the YY mode
;;;; WARNING: grammar rule `head-opt-comp' is loopy
;;;; WARNING: edge #2923 [head-opt-comp] == edge #2910 [head-opt-comp]
;generic_vv := main-verb-lex &
; [ SYNSEM.LKEYS.KEYREL.PRED #pred,
; STEM < "_generic_verb_" >,
; TOKENS.+LIST generic_token_list &
; < [ +POS.+TAGS < "VV" >,
; +PRED #pred ] > ].
;; Temporally, it is assumed as a transitive verb
generic_vv := v_trans-verb-lex &
[ SYNSEM.LKEYS.KEYREL.PRED #pred,
STEM < "_generic_vv_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "VV" >,
+PRED #pred ] > ].
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
generic_va := pred-adj-lex &
[ SYNSEM.LKEYS.KEYREL.PRED #pred,
STEM < "_generic_va_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "VA" >,
+PRED #pred ] > ].
generic_jj := attr-adj-lex &
[ SYNSEM.LKEYS.KEYREL.PRED #pred,
STEM < "_generic_jj_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "JJ" >,
+PRED #pred ] > ].
generic_ij := interjection-lex &
[ SYNSEM.LKEYS.KEYREL.PRED #pred,
STEM < "_generic_ij_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "VA" >,
+PRED #pred ] > ].
generic_pu := symbol &
[ SYNSEM.LKEYS.KEYREL.CARG #carg,
STEM < "_generic_pu_" >,
TOKENS.+LIST generic_token_list &
< [ +POS.+TAGS < "PU" >,
+CARG #carg ] > ].
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
generic_num_ne := num-adj-lex &
[ SYNSEM.LKEYS.KEYREL.CARG #carg,
STEM < "_generic_num_ne_" >,
TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
+CARG #carg,
+CLASS card_ne ] > ].
generic_year_ne := time-noun-lex & nonque-item &
[ SYNSEM.LKEYS.KEYREL.CARG #carg,
STEM < "_generic_year_ne_" >,
TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
+CARG #carg,
+CLASS year_ne ] > ].
; generic_month_ne := time-noun-lex & nonque-item &
; [ SYNSEM.LKEYS.KEYREL [ PRED month_n_rel,
; CARG #carg ],
; STEM < "_generic_month_ne_" >,
; TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
; +CARG #carg,
; +CLASS month_ne ] > ].
; generic_day_ne := time-noun-lex & nonque-item &
; [ SYNSEM.LKEYS.KEYREL [ PRED day_n_rel,
; CARG #carg ],
; STEM < "_generic_day_ne_" >,
; TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
; +CARG #carg,
; +CLASS day_ne ] > ].
generic_date_ne := time-noun-lex & nonque-item &
[ SYNSEM.LKEYS.KEYREL [ PRED date_n_rel,
CARG #carg ],
STEM < "_generic_date_ne_" >,
TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
+CARG #carg,
+CLASS date_ne ] > ].
generic_time_noun_ne := time-noun-lex & nonque-item &
[ SYNSEM.LKEYS.KEYREL [ PRED time_n_rel,
CARG #carg ],
STEM < "_generic_time_ne_" >,
TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
+CARG #carg,
+CLASS time_ne ] > ].
; generic_email_noun_ne := proper-name-lex & nonque-item &
; [ SYNSEM.LKEYS.KEYREL [ PRED named_rel,
; CARG #carg ],
; STEM < "_generic_email_ne_" >,
; TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
; +CARG #carg,
; +CLASS email_ne ] > ].
;;for numeral phrases like "五号", treating as proper noun temporarily
generic_meas_noun_ne := proper-name-lex & nonque-item &
[ SYNSEM.LKEYS.KEYREL [ PRED named_rel,
CARG #carg ],
STEM < "_generic_meas_ne_" >,
TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
+CARG #carg,
+CLASS meas_ne ] > ].
generic_proper_ne := proper-name-lex & nonque-item &
[ SYNSEM.LKEYS.KEYREL [ PRED named_rel,
CARG #carg ],
STEM < "_generic_name_ne_" >,
TOKENS.+LIST generic_token_list & < [ +POS.+TAGS null,
+CARG #carg,
+CLASS proper_ne ] > ].
; generic_trans_verb_bse := v_np*_bse-unk_le &
; [ ORTH < "_generic_vb_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VB" ] > ].
; generic_trans_verb_pres3sg := v_np*_pr-3s-unk_le &
; [ ORTH < "_generic_vbz_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VBZ" ] > ].
; generic_trans_verb_presn3sg := v_np*_pr-n3s-unk_le &
; [ ORTH < "_generic_vbp_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VBP" ] > ].
; generic_trans_verb_past := v_np*_pa-unk_le &
; [ ORTH < "_generic_vbd_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VBD" ] > ].
; generic_trans_verb_prp := v_np*_prp-unk_le &
; [ ORTH < "_generic_vbg_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VBG" ] > ].
; generic_trans_verb_psp := v_np*_psp-unk_le &
; [ ORTH < "_generic_vbn_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VBN" ] > ].
; generic_trans_verb_pas := v_-_pas-unk_le &
; [ ORTH < "_generic_vbn_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "VBN" ] > ].
; generic_mass_noun := n_-_mc-unk_le &
; [ ORTH < "_generic_fw_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "FW" ] > ].
; generic_mass_count_noun := n_-_mc-unk_le &
; [ ORTH < "_generic_nn_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "NN" ] > ].
; generic_pl_noun := n_-_c-pl-unk_le &
; [ ORTH < "_generic_nns_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "NNS" ] > ].
; genericname := n_-_pn-unk_le &
; [ ORTH < "_generic_nnp_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "NNP" ] > ].
; genericname_pl := n_-_pn-pl-unk_le &
; [ ORTH < "_generic_nnps_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "NNPS" ] > ].
; generic_adj := aj_-_i-unk_le &
; [ ORTH < "_generic_jj_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "JJ" ] > ].
; generic_adj_compar := aj_-_i-cmp-unk_le &
; [ ORTH < "_generic_jjr_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "JJR" ] > ].
; generic_adj_superl := aj_-_i-sup-unk_le &
; [ ORTH < "_generic_jjs_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "JJS" ] > ].
; generic_number := aj_-_i-crd-unk_le &
; [ ORTH < "_generic_cd_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "CD" ] > ].
; generic_adverb := av_-_i-unk_le &
; [ ORTH < "_generic_rb_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "RB" ] > ].
; generic_uh_disc_adv := av_-_dc-like-unk_le &
; [ ORTH < "_generic_uh_" >,
; TOKENS.+LIST < [ +TNT.+TAGS.FIRST "UH" ] > ].
; ;;;
; ;;; and the second group of `generic' named entities, activated by their +CLASS
; ;;; values, which get set in token mapping. to avoid overlap with the unknown
; ;;; lexical entries, the token mapping rules make sure to `empty out' the PoS
; ;;; information whenever a named entity token is created.
; ;;;
; generic_proper_ne := n_-_pn-gen_le &
; [ ORTH < "_generic_proper_ne_" >,
; TOKENS.+LIST < [ +CLASS proper_ne ] > ].
; generic_pl_noun_ne := n_-_c-pl-gen_le &
; [ ORTH < "_generic_plur_ne_" >,
; TOKENS.+LIST < [ +CLASS plur_ne ] > ].
; generic_date_ne := n_-_day-crd-gen_le &
; [ ORTH < "_generic_date_ne_" >,
; TOKENS.+LIST < [ +CLASS date_ne ] > ].
; generic_dom_card_ne := n_-_pn-dom-gen_le &
; [ ORTH < "_generic_dom_card_ne_" >,
; TOKENS.+LIST < [ +CLASS dom_card_ne ] > ].
; generic_dom_ord_ne := n_-_pn-dom-o-gen_le &
; [ ORTH < "_generic_dom_ord_ne_" >,
; TOKENS.+LIST < [ +CLASS dom_ord_ne ] > ].
; generic_dom_euro_ne := n_-_pn-dom-e-gen_le &
; [ ORTH < "_generic_dom_euro_ne_" >,
; TOKENS.+LIST < [ +CLASS dom_card_ne ] > ].
; generic_year_ne := n_-_pn-yoc-gen_le &
; [ ORTH < "_generic_year_ne_" >,
; TOKENS.+LIST < [ +CLASS year_ne ] > ].
; generic_meas_np_ne := n_-_meas-gen_le &
; [ ORTH < "_generic_meas_np_ne_" >,
; TOKENS.+LIST < [ +CLASS meas_ne ] > ].
; generic_meas_n_ne := n_-_meas-n-gen_le &
; [ ORTH < "_generic_meas_noun_ne_" >,
; TOKENS.+LIST < [ +CLASS meas_noun_ne ] > ].
; generic_time_noun_ne := n_np_pn-hour-gen_le &
; [ ORTH < "_generic_time_ne_" >,
; TOKENS.+LIST < [ +CLASS time_ne ] > ].
; generic_card_ne := aj_-_i-crd-gen_le &
; [ ORTH < "_generic_card_ne_" >,
; TOKENS.+LIST < [ +CLASS card_ne ] > ].
; generic_card_np_ne := aj_np_i-crd-gen_le &
; [ ORTH < "_generic_card_ne_" >,
; TOKENS.+LIST < [ +CLASS card_ne ] > ].
; generic_ord_ne := aj_-_i-ord-gen_le &
; [ ORTH < "_generic_ord_ne_" >,
; TOKENS.+LIST < [ +CLASS ord_ne ] > ].
; generic_fract_ne := aj_-_i-frct-gen_le &
; [ ORTH < "_generic_fract_ne_" >,
; TOKENS.+LIST < [ +CLASS frct_ne ] > ].
; generic_decimal_ne := aj_-_i-one-gen_le &
; [ ORTH < "_generic_decimal_ne_" >,
; TOKENS.+LIST < [ +CLASS decimal_ne ] > ].
; gen_generic_noun := n_-_mc-ns-g_le &
; [ ORTH < "_gen_generic_noun_" >,
; TOKENS.+LIST < [ +CLASS no_class ] > ].
; gen_generic_verb := v_np*_unk_le &
; [ ORTH < "_gen_generic_verb_" >,
; TOKENS.+LIST < [ +CLASS no_class ] > ].