nltk 3.2__zip → 3.3__zip

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (406) hide show
  1. {nltk-3.2 → nltk-3.3}/INSTALL.txt +6 -6
  2. {nltk-3.2 → nltk-3.3}/LICENSE.txt +13 -13
  3. {nltk-3.2 → nltk-3.3}/MANIFEST.in +6 -6
  4. {nltk-3.2/nltk.egg-info → nltk-3.3}/PKG-INFO +13 -5
  5. nltk-3.2/README.txt → nltk-3.3/README.md +49 -48
  6. nltk-3.3/nltk/VERSION +1 -0
  7. {nltk-3.2 → nltk-3.3}/nltk/__init__.py +185 -185
  8. {nltk-3.2 → nltk-3.3}/nltk/app/__init__.py +52 -53
  9. {nltk-3.2 → nltk-3.3}/nltk/app/chartparser_app.py +2276 -2276
  10. {nltk-3.2 → nltk-3.3}/nltk/app/chunkparser_app.py +1262 -1264
  11. {nltk-3.2 → nltk-3.3}/nltk/app/collocations_app.py +347 -350
  12. {nltk-3.2 → nltk-3.3}/nltk/app/concordance_app.py +568 -570
  13. {nltk-3.2 → nltk-3.3}/nltk/app/nemo_app.py +156 -155
  14. {nltk-3.2 → nltk-3.3}/nltk/app/rdparser_app.py +892 -894
  15. {nltk-3.2 → nltk-3.3}/nltk/app/srparser_app.py +809 -809
  16. {nltk-3.2 → nltk-3.3}/nltk/app/wordfreq_app.py +32 -32
  17. {nltk-3.2 → nltk-3.3}/nltk/app/wordnet_app.py +968 -968
  18. {nltk-3.2 → nltk-3.3}/nltk/book.py +91 -90
  19. {nltk-3.2 → nltk-3.3}/nltk/ccg/__init__.py +22 -22
  20. {nltk-3.2 → nltk-3.3}/nltk/ccg/api.py +359 -335
  21. {nltk-3.2 → nltk-3.3}/nltk/ccg/chart.py +394 -361
  22. {nltk-3.2 → nltk-3.3}/nltk/ccg/combinator.py +343 -312
  23. {nltk-3.2 → nltk-3.3}/nltk/ccg/lexicon.py +328 -290
  24. nltk-3.3/nltk/ccg/logic.py +46 -0
  25. {nltk-3.2 → nltk-3.3}/nltk/chat/__init__.py +49 -49
  26. {nltk-3.2 → nltk-3.3}/nltk/chat/eliza.py +244 -244
  27. {nltk-3.2 → nltk-3.3}/nltk/chat/iesha.py +140 -140
  28. {nltk-3.2 → nltk-3.3}/nltk/chat/rude.py +92 -92
  29. {nltk-3.2 → nltk-3.3}/nltk/chat/suntsu.py +117 -117
  30. {nltk-3.2 → nltk-3.3}/nltk/chat/util.py +122 -120
  31. {nltk-3.2 → nltk-3.3}/nltk/chat/zen.py +282 -282
  32. {nltk-3.2 → nltk-3.3}/nltk/chunk/__init__.py +190 -190
  33. {nltk-3.2 → nltk-3.3}/nltk/chunk/api.py +51 -51
  34. {nltk-3.2 → nltk-3.3}/nltk/chunk/named_entity.py +331 -331
  35. {nltk-3.2 → nltk-3.3}/nltk/chunk/regexp.py +1390 -1384
  36. {nltk-3.2 → nltk-3.3}/nltk/chunk/util.py +600 -600
  37. {nltk-3.2 → nltk-3.3}/nltk/classify/__init__.py +98 -98
  38. {nltk-3.2 → nltk-3.3}/nltk/classify/api.py +193 -193
  39. {nltk-3.2 → nltk-3.3}/nltk/classify/decisiontree.py +295 -295
  40. {nltk-3.2 → nltk-3.3}/nltk/classify/maxent.py +1510 -1492
  41. {nltk-3.2 → nltk-3.3}/nltk/classify/megam.py +179 -178
  42. {nltk-3.2 → nltk-3.3}/nltk/classify/naivebayes.py +245 -242
  43. {nltk-3.2 → nltk-3.3}/nltk/classify/positivenaivebayes.py +170 -170
  44. {nltk-3.2 → nltk-3.3}/nltk/classify/rte_classify.py +160 -191
  45. {nltk-3.2 → nltk-3.3}/nltk/classify/scikitlearn.py +153 -151
  46. {nltk-3.2 → nltk-3.3}/nltk/classify/senna.py +183 -181
  47. {nltk-3.2 → nltk-3.3}/nltk/classify/svm.py +15 -15
  48. {nltk-3.2 → nltk-3.3}/nltk/classify/tadm.py +113 -112
  49. {nltk-3.2 → nltk-3.3}/nltk/classify/textcat.py +193 -193
  50. {nltk-3.2 → nltk-3.3}/nltk/classify/util.py +324 -312
  51. {nltk-3.2 → nltk-3.3}/nltk/classify/weka.py +346 -345
  52. {nltk-3.2 → nltk-3.3}/nltk/cluster/__init__.py +86 -86
  53. {nltk-3.2 → nltk-3.3}/nltk/cluster/api.py +74 -70
  54. {nltk-3.2 → nltk-3.3}/nltk/cluster/em.py +247 -247
  55. {nltk-3.2 → nltk-3.3}/nltk/cluster/gaac.py +168 -168
  56. {nltk-3.2 → nltk-3.3}/nltk/cluster/kmeans.py +221 -221
  57. {nltk-3.2 → nltk-3.3}/nltk/cluster/util.py +304 -289
  58. nltk-3.3/nltk/collections.py +640 -0
  59. {nltk-3.2 → nltk-3.3}/nltk/collocations.py +388 -388
  60. nltk-3.3/nltk/compat.py +365 -0
  61. {nltk-3.2 → nltk-3.3}/nltk/corpus/__init__.py +341 -320
  62. {nltk-3.2 → nltk-3.3}/nltk/corpus/europarl_raw.py +44 -44
  63. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/__init__.py +147 -145
  64. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/aligned.py +115 -114
  65. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/api.py +448 -446
  66. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/bnc.py +252 -252
  67. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/bracket_parse.py +227 -227
  68. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/categorized_sents.py +179 -178
  69. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/chasen.py +140 -139
  70. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/childes.py +522 -494
  71. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/chunked.py +212 -212
  72. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/cmudict.py +97 -95
  73. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/comparative_sents.py +280 -278
  74. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/conll.py +528 -521
  75. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/crubadan.py +116 -116
  76. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/dependency.py +101 -101
  77. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/framenet.py +3059 -2093
  78. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ieer.py +112 -111
  79. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/indian.py +85 -86
  80. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ipipan.py +332 -331
  81. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/knbc.py +187 -187
  82. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/lin.py +156 -156
  83. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/mte.py +311 -310
  84. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nkjp.py +429 -428
  85. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nombank.py +421 -421
  86. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/nps_chat.py +73 -73
  87. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/opinion_lexicon.py +115 -115
  88. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/panlex_lite.py +165 -165
  89. nltk-3.3/nltk/corpus/reader/pl196x.py +292 -0
  90. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/plaintext.py +232 -233
  91. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ppattach.py +96 -95
  92. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/propbank.py +479 -481
  93. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/pros_cons.py +128 -126
  94. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/reviews.py +330 -328
  95. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/rte.py +144 -146
  96. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/semcor.py +256 -256
  97. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/senseval.py +203 -201
  98. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/sentiwordnet.py +137 -137
  99. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/sinica_treebank.py +75 -75
  100. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/string_category.py +60 -59
  101. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/switchboard.py +119 -119
  102. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/tagged.py +295 -294
  103. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/timit.py +452 -450
  104. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/toolbox.py +68 -68
  105. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/twitter.py +155 -157
  106. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/udhr.py +80 -80
  107. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/util.py +804 -800
  108. nltk-3.3/nltk/corpus/reader/verbnet.py +595 -0
  109. nltk-3.3/nltk/corpus/reader/wordlist.py +134 -0
  110. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/wordnet.py +2108 -2036
  111. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/xmldocs.py +392 -387
  112. {nltk-3.2 → nltk-3.3}/nltk/corpus/reader/ycoe.py +243 -242
  113. {nltk-3.2 → nltk-3.3}/nltk/corpus/util.py +144 -127
  114. {nltk-3.2 → nltk-3.3}/nltk/data.py +1487 -1451
  115. {nltk-3.2 → nltk-3.3}/nltk/decorators.py +219 -215
  116. {nltk-3.2 → nltk-3.3}/nltk/downloader.py +2278 -2274
  117. {nltk-3.2 → nltk-3.3}/nltk/draw/__init__.py +27 -27
  118. {nltk-3.2 → nltk-3.3}/nltk/draw/cfg.py +774 -777
  119. {nltk-3.2 → nltk-3.3}/nltk/draw/dispersion.py +58 -58
  120. {nltk-3.2 → nltk-3.3}/nltk/draw/table.py +1098 -1098
  121. {nltk-3.2 → nltk-3.3}/nltk/draw/tree.py +963 -966
  122. {nltk-3.2 → nltk-3.3}/nltk/draw/util.py +2356 -2356
  123. {nltk-3.2 → nltk-3.3}/nltk/featstruct.py +2617 -2500
  124. {nltk-3.2 → nltk-3.3}/nltk/grammar.py +1559 -1516
  125. {nltk-3.2 → nltk-3.3}/nltk/help.py +56 -56
  126. {nltk-3.2 → nltk-3.3}/nltk/inference/__init__.py +20 -20
  127. {nltk-3.2 → nltk-3.3}/nltk/inference/api.py +597 -589
  128. {nltk-3.2 → nltk-3.3}/nltk/inference/discourse.py +612 -608
  129. {nltk-3.2 → nltk-3.3}/nltk/inference/mace.py +311 -311
  130. {nltk-3.2 → nltk-3.3}/nltk/inference/nonmonotonic.py +509 -509
  131. {nltk-3.2 → nltk-3.3}/nltk/inference/prover9.py +431 -431
  132. {nltk-3.2 → nltk-3.3}/nltk/inference/resolution.py +687 -687
  133. {nltk-3.2 → nltk-3.3}/nltk/inference/tableau.py +607 -607
  134. {nltk-3.2 → nltk-3.3}/nltk/internals.py +982 -982
  135. {nltk-3.2 → nltk-3.3}/nltk/jsontags.py +63 -63
  136. {nltk-3.2 → nltk-3.3}/nltk/lazyimport.py +142 -142
  137. {nltk-3.2 → nltk-3.3}/nltk/metrics/__init__.py +30 -29
  138. {nltk-3.2 → nltk-3.3}/nltk/metrics/agreement.py +421 -401
  139. nltk-3.3/nltk/metrics/aline.py +607 -0
  140. {nltk-3.2 → nltk-3.3}/nltk/metrics/association.py +414 -410
  141. {nltk-3.2 → nltk-3.3}/nltk/metrics/confusionmatrix.py +206 -206
  142. {nltk-3.2 → nltk-3.3}/nltk/metrics/distance.py +207 -202
  143. {nltk-3.2 → nltk-3.3}/nltk/metrics/paice.py +381 -381
  144. {nltk-3.2 → nltk-3.3}/nltk/metrics/scores.py +228 -228
  145. {nltk-3.2 → nltk-3.3}/nltk/metrics/segmentation.py +231 -232
  146. {nltk-3.2 → nltk-3.3}/nltk/metrics/spearman.py +69 -69
  147. {nltk-3.2 → nltk-3.3}/nltk/misc/__init__.py +11 -11
  148. {nltk-3.2 → nltk-3.3}/nltk/misc/babelfish.py +10 -10
  149. {nltk-3.2 → nltk-3.3}/nltk/misc/chomsky.py +135 -133
  150. {nltk-3.2 → nltk-3.3}/nltk/misc/minimalset.py +83 -83
  151. {nltk-3.2 → nltk-3.3}/nltk/misc/sort.py +157 -157
  152. {nltk-3.2 → nltk-3.3}/nltk/misc/wordfinder.py +129 -129
  153. {nltk-3.2 → nltk-3.3}/nltk/parse/__init__.py +81 -80
  154. {nltk-3.2 → nltk-3.3}/nltk/parse/api.py +66 -66
  155. {nltk-3.2 → nltk-3.3}/nltk/parse/bllip.py +282 -282
  156. {nltk-3.2 → nltk-3.3}/nltk/parse/chart.py +1682 -1681
  157. nltk-3.3/nltk/parse/corenlp.py +780 -0
  158. {nltk-3.2 → nltk-3.3}/nltk/parse/dependencygraph.py +760 -758
  159. {nltk-3.2 → nltk-3.3}/nltk/parse/earleychart.py +452 -451
  160. {nltk-3.2 → nltk-3.3}/nltk/parse/evaluate.py +129 -129
  161. {nltk-3.2 → nltk-3.3}/nltk/parse/featurechart.py +580 -578
  162. {nltk-3.2 → nltk-3.3}/nltk/parse/generate.py +87 -76
  163. {nltk-3.2 → nltk-3.3}/nltk/parse/malt.py +356 -356
  164. {nltk-3.2 → nltk-3.3}/nltk/parse/nonprojectivedependencyparser.py +783 -783
  165. {nltk-3.2 → nltk-3.3}/nltk/parse/pchart.py +522 -522
  166. {nltk-3.2 → nltk-3.3}/nltk/parse/projectivedependencyparser.py +579 -578
  167. {nltk-3.2 → nltk-3.3}/nltk/parse/recursivedescent.py +655 -656
  168. {nltk-3.2 → nltk-3.3}/nltk/parse/shiftreduce.py +458 -459
  169. {nltk-3.2 → nltk-3.3}/nltk/parse/stanford.py +431 -406
  170. {nltk-3.2 → nltk-3.3}/nltk/parse/transitionparser.py +774 -772
  171. {nltk-3.2 → nltk-3.3}/nltk/parse/util.py +231 -231
  172. {nltk-3.2 → nltk-3.3}/nltk/parse/viterbi.py +401 -401
  173. {nltk-3.2 → nltk-3.3}/nltk/probability.py +2410 -2355
  174. {nltk-3.2 → nltk-3.3}/nltk/sem/__init__.py +61 -61
  175. {nltk-3.2 → nltk-3.3}/nltk/sem/boxer.py +1261 -1261
  176. {nltk-3.2 → nltk-3.3}/nltk/sem/chat80.py +782 -782
  177. {nltk-3.2 → nltk-3.3}/nltk/sem/cooper_storage.py +118 -118
  178. {nltk-3.2 → nltk-3.3}/nltk/sem/drt.py +1258 -1257
  179. {nltk-3.2 → nltk-3.3}/nltk/sem/drt_glue_demo.py +485 -489
  180. {nltk-3.2 → nltk-3.3}/nltk/sem/evaluate.py +790 -784
  181. {nltk-3.2 → nltk-3.3}/nltk/sem/glue.py +696 -694
  182. {nltk-3.2 → nltk-3.3}/nltk/sem/hole.py +386 -384
  183. {nltk-3.2 → nltk-3.3}/nltk/sem/lfg.py +210 -208
  184. {nltk-3.2 → nltk-3.3}/nltk/sem/linearlogic.py +451 -449
  185. {nltk-3.2 → nltk-3.3}/nltk/sem/logic.py +1910 -1910
  186. {nltk-3.2 → nltk-3.3}/nltk/sem/relextract.py +476 -483
  187. {nltk-3.2 → nltk-3.3}/nltk/sem/skolemize.py +101 -101
  188. {nltk-3.2 → nltk-3.3}/nltk/sem/util.py +249 -249
  189. {nltk-3.2 → nltk-3.3}/nltk/sentiment/__init__.py +14 -14
  190. {nltk-3.2 → nltk-3.3}/nltk/sentiment/sentiment_analyzer.py +229 -229
  191. {nltk-3.2 → nltk-3.3}/nltk/sentiment/util.py +762 -752
  192. {nltk-3.2 → nltk-3.3}/nltk/sentiment/vader.py +443 -445
  193. {nltk-3.2 → nltk-3.3}/nltk/stem/__init__.py +31 -33
  194. {nltk-3.2 → nltk-3.3}/nltk/stem/api.py +28 -25
  195. nltk-3.3/nltk/stem/arlstem.py +369 -0
  196. {nltk-3.2 → nltk-3.3}/nltk/stem/isri.py +345 -345
  197. {nltk-3.2 → nltk-3.3}/nltk/stem/lancaster.py +337 -310
  198. nltk-3.3/nltk/stem/porter.py +710 -0
  199. {nltk-3.2 → nltk-3.3}/nltk/stem/regexp.py +61 -61
  200. {nltk-3.2 → nltk-3.3}/nltk/stem/rslp.py +142 -142
  201. {nltk-3.2 → nltk-3.3}/nltk/stem/snowball.py +4236 -3712
  202. {nltk-3.2 → nltk-3.3}/nltk/stem/util.py +22 -12
  203. {nltk-3.2 → nltk-3.3}/nltk/stem/wordnet.py +51 -51
  204. {nltk-3.2 → nltk-3.3}/nltk/tag/__init__.py +152 -127
  205. {nltk-3.2 → nltk-3.3}/nltk/tag/api.py +86 -81
  206. {nltk-3.2 → nltk-3.3}/nltk/tag/brill.py +424 -426
  207. {nltk-3.2 → nltk-3.3}/nltk/tag/brill_trainer.py +608 -608
  208. {nltk-3.2 → nltk-3.3}/nltk/tag/crf.py +204 -200
  209. {nltk-3.2 → nltk-3.3}/nltk/tag/hmm.py +1277 -1277
  210. {nltk-3.2 → nltk-3.3}/nltk/tag/hunpos.py +132 -132
  211. {nltk-3.2 → nltk-3.3}/nltk/tag/mapping.py +101 -101
  212. {nltk-3.2 → nltk-3.3}/nltk/tag/perceptron.py +329 -314
  213. {nltk-3.2 → nltk-3.3}/nltk/tag/senna.py +147 -145
  214. {nltk-3.2 → nltk-3.3}/nltk/tag/sequential.py +740 -736
  215. {nltk-3.2 → nltk-3.3}/nltk/tag/stanford.py +219 -196
  216. {nltk-3.2 → nltk-3.3}/nltk/tag/tnt.py +595 -604
  217. {nltk-3.2 → nltk-3.3}/nltk/tag/util.py +72 -72
  218. {nltk-3.2 → nltk-3.3}/nltk/tbl/__init__.py +28 -28
  219. {nltk-3.2 → nltk-3.3}/nltk/tbl/api.py +1 -1
  220. {nltk-3.2 → nltk-3.3}/nltk/tbl/demo.py +366 -366
  221. {nltk-3.2 → nltk-3.3}/nltk/tbl/erroranalysis.py +39 -39
  222. {nltk-3.2 → nltk-3.3}/nltk/tbl/feature.py +259 -261
  223. {nltk-3.2 → nltk-3.3}/nltk/tbl/rule.py +321 -321
  224. {nltk-3.2 → nltk-3.3}/nltk/tbl/template.py +303 -308
  225. {nltk-3.2 → nltk-3.3}/nltk/test/__init__.py +18 -18
  226. {nltk-3.2 → nltk-3.3}/nltk/test/all.py +24 -23
  227. {nltk-3.2 → nltk-3.3}/nltk/test/bleu.doctest +14 -14
  228. {nltk-3.2 → nltk-3.3}/nltk/test/bnc.doctest +60 -60
  229. {nltk-3.2 → nltk-3.3}/nltk/test/ccg.doctest +376 -395
  230. nltk-3.3/nltk/test/ccg_semantics.doctest +553 -0
  231. {nltk-3.2 → nltk-3.3}/nltk/test/chat80.doctest +234 -234
  232. {nltk-3.2 → nltk-3.3}/nltk/test/childes.doctest +184 -184
  233. {nltk-3.2 → nltk-3.3}/nltk/test/childes_fixt.py +14 -13
  234. {nltk-3.2 → nltk-3.3}/nltk/test/chunk.doctest +373 -373
  235. {nltk-3.2 → nltk-3.3}/nltk/test/classify.doctest +185 -185
  236. {nltk-3.2 → nltk-3.3}/nltk/test/classify_fixt.py +11 -10
  237. nltk-3.3/nltk/test/collections.doctest +20 -0
  238. {nltk-3.2 → nltk-3.3}/nltk/test/collocations.doctest +276 -276
  239. {nltk-3.2 → nltk-3.3}/nltk/test/compat.doctest +134 -138
  240. {nltk-3.2 → nltk-3.3}/nltk/test/compat_fixt.py +9 -8
  241. nltk-3.3/nltk/test/concordance.doctest +55 -0
  242. {nltk-3.2 → nltk-3.3}/nltk/test/corpus.doctest +2200 -2212
  243. {nltk-3.2 → nltk-3.3}/nltk/test/corpus_fixt.py +3 -3
  244. {nltk-3.2 → nltk-3.3}/nltk/test/crubadan.doctest +65 -65
  245. {nltk-3.2 → nltk-3.3}/nltk/test/data.doctest +379 -379
  246. {nltk-3.2 → nltk-3.3}/nltk/test/dependency.doctest +241 -241
  247. {nltk-3.2 → nltk-3.3}/nltk/test/discourse.doctest +546 -546
  248. {nltk-3.2 → nltk-3.3}/nltk/test/discourse_fixt.py +14 -13
  249. {nltk-3.2 → nltk-3.3}/nltk/test/doctest_nose_plugin.py +159 -156
  250. {nltk-3.2 → nltk-3.3}/nltk/test/drt.doctest +517 -517
  251. {nltk-3.2 → nltk-3.3}/nltk/test/featgram.doctest +607 -607
  252. {nltk-3.2 → nltk-3.3}/nltk/test/featstruct.doctest +1229 -1230
  253. {nltk-3.2 → nltk-3.3}/nltk/test/framenet.doctest +288 -239
  254. {nltk-3.2 → nltk-3.3}/nltk/test/generate.doctest +67 -67
  255. {nltk-3.2 → nltk-3.3}/nltk/test/gensim.doctest +140 -141
  256. {nltk-3.2 → nltk-3.3}/nltk/test/gensim_fixt.py +10 -9
  257. {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics.doctest +384 -386
  258. {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics_malt.doctest +68 -68
  259. {nltk-3.2 → nltk-3.3}/nltk/test/gluesemantics_malt_fixt.py +12 -11
  260. {nltk-3.2 → nltk-3.3}/nltk/test/grammar.doctest +48 -48
  261. {nltk-3.2 → nltk-3.3}/nltk/test/grammartestsuites.doctest +109 -109
  262. {nltk-3.2 → nltk-3.3}/nltk/test/index.doctest +100 -100
  263. {nltk-3.2 → nltk-3.3}/nltk/test/inference.doctest +534 -534
  264. {nltk-3.2 → nltk-3.3}/nltk/test/inference_fixt.py +12 -11
  265. {nltk-3.2 → nltk-3.3}/nltk/test/internals.doctest +140 -140
  266. {nltk-3.2 → nltk-3.3}/nltk/test/japanese.doctest +48 -48
  267. {nltk-3.2 → nltk-3.3}/nltk/test/logic.doctest +1098 -1098
  268. {nltk-3.2 → nltk-3.3}/nltk/test/metrics.doctest +270 -270
  269. {nltk-3.2 → nltk-3.3}/nltk/test/misc.doctest +118 -118
  270. {nltk-3.2 → nltk-3.3}/nltk/test/nonmonotonic.doctest +286 -286
  271. {nltk-3.2 → nltk-3.3}/nltk/test/nonmonotonic_fixt.py +12 -11
  272. {nltk-3.2 → nltk-3.3}/nltk/test/paice.doctest +35 -35
  273. {nltk-3.2 → nltk-3.3}/nltk/test/parse.doctest +884 -884
  274. {nltk-3.2 → nltk-3.3}/nltk/test/portuguese_en.doctest +565 -565
  275. {nltk-3.2 → nltk-3.3}/nltk/test/portuguese_en_fixt.py +16 -16
  276. {nltk-3.2 → nltk-3.3}/nltk/test/probability.doctest +304 -304
  277. {nltk-3.2 → nltk-3.3}/nltk/test/probability_fixt.py +13 -12
  278. {nltk-3.2 → nltk-3.3}/nltk/test/propbank.doctest +176 -176
  279. {nltk-3.2 → nltk-3.3}/nltk/test/relextract.doctest +263 -263
  280. {nltk-3.2 → nltk-3.3}/nltk/test/resolution.doctest +221 -221
  281. {nltk-3.2 → nltk-3.3}/nltk/test/runtests.py +86 -64
  282. {nltk-3.2 → nltk-3.3}/nltk/test/segmentation_fixt.py +10 -10
  283. {nltk-3.2 → nltk-3.3}/nltk/test/semantics.doctest +665 -665
  284. {nltk-3.2 → nltk-3.3}/nltk/test/semantics_fixt.py +7 -7
  285. {nltk-3.2 → nltk-3.3}/nltk/test/sentiment.doctest +233 -233
  286. {nltk-3.2 → nltk-3.3}/nltk/test/sentiwordnet.doctest +41 -41
  287. {nltk-3.2 → nltk-3.3}/nltk/test/simple.doctest +85 -85
  288. {nltk-3.2 → nltk-3.3}/nltk/test/stem.doctest +78 -78
  289. {nltk-3.2 → nltk-3.3}/nltk/test/tag.doctest +33 -33
  290. {nltk-3.2 → nltk-3.3}/nltk/test/tokenize.doctest +273 -166
  291. {nltk-3.2 → nltk-3.3}/nltk/test/toolbox.doctest +307 -307
  292. {nltk-3.2 → nltk-3.3}/nltk/test/translate.doctest +242 -242
  293. {nltk-3.2 → nltk-3.3}/nltk/test/translate_fixt.py +3 -3
  294. {nltk-3.2 → nltk-3.3}/nltk/test/tree.doctest +1101 -1101
  295. {nltk-3.2 → nltk-3.3}/nltk/test/treeprettyprinter.doctest +127 -127
  296. {nltk-3.2 → nltk-3.3}/nltk/test/treetransforms.doctest +156 -156
  297. nltk-3.3/nltk/test/unit/test_2x_compat.py +63 -0
  298. nltk-3.3/nltk/test/unit/test_aline.py +52 -0
  299. nltk-3.3/nltk/test/unit/test_chunk.py +56 -0
  300. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_classify.py +55 -53
  301. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_collocations.py +88 -79
  302. nltk-3.3/nltk/test/unit/test_concordance.py +98 -0
  303. nltk-3.3/nltk/test/unit/test_corenlp.py +1000 -0
  304. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_corpora.py +200 -183
  305. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_corpus_views.py +45 -45
  306. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_hmm.py +88 -88
  307. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_json2csv_corpus.py +188 -187
  308. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_naivebayes.py +26 -26
  309. nltk-3.3/nltk/test/unit/test_rte_classify.py +86 -0
  310. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_seekable_unicode_stream_reader.py +124 -124
  311. nltk-3.3/nltk/test/unit/test_senna.py +74 -0
  312. nltk-3.3/nltk/test/unit/test_stem.py +121 -0
  313. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_tag.py +20 -20
  314. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_tgrep.py +628 -626
  315. nltk-3.3/nltk/test/unit/test_tokenize.py +168 -0
  316. {nltk-3.2 → nltk-3.3}/nltk/test/unit/test_twitter_auth.py +185 -185
  317. nltk-3.3/nltk/test/unit/test_wordnet.py +134 -0
  318. nltk-3.3/nltk/test/unit/translate/test_bleu.py +244 -0
  319. nltk-3.3/nltk/test/unit/translate/test_gdfa.py +57 -0
  320. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm1.py +75 -75
  321. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm2.py +87 -87
  322. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm3.py +105 -105
  323. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm4.py +126 -126
  324. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm5.py +166 -166
  325. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_ibm_model.py +270 -270
  326. nltk-3.3/nltk/test/unit/translate/test_nist.py +37 -0
  327. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/test_stack_decoder.py +300 -300
  328. {nltk-3.2 → nltk-3.3}/nltk/test/unit/utils.py +41 -41
  329. {nltk-3.2 → nltk-3.3}/nltk/test/util.doctest +48 -48
  330. {nltk-3.2 → nltk-3.3}/nltk/test/wordnet.doctest +595 -581
  331. {nltk-3.2 → nltk-3.3}/nltk/test/wordnet_fixt.py +7 -6
  332. {nltk-3.2 → nltk-3.3}/nltk/test/wordnet_lch.doctest +53 -53
  333. {nltk-3.2 → nltk-3.3}/nltk/test/wsd.doctest +68 -68
  334. {nltk-3.2 → nltk-3.3}/nltk/text.py +663 -610
  335. {nltk-3.2 → nltk-3.3}/nltk/tgrep.py +938 -937
  336. {nltk-3.2 → nltk-3.3}/nltk/tokenize/__init__.py +130 -107
  337. {nltk-3.2 → nltk-3.3}/nltk/tokenize/api.py +77 -78
  338. {nltk-3.2 → nltk-3.3}/nltk/tokenize/casual.py +343 -342
  339. {nltk-3.2 → nltk-3.3}/nltk/tokenize/mwe.py +120 -120
  340. nltk-3.3/nltk/tokenize/nist.py +173 -0
  341. {nltk-3.2 → nltk-3.3}/nltk/tokenize/punkt.py +1620 -1601
  342. {nltk-3.2 → nltk-3.3}/nltk/tokenize/regexp.py +208 -202
  343. nltk-3.3/nltk/tokenize/repp.py +151 -0
  344. {nltk-3.2 → nltk-3.3}/nltk/tokenize/sexpr.py +140 -142
  345. {nltk-3.2 → nltk-3.3}/nltk/tokenize/simple.py +138 -136
  346. {nltk-3.2 → nltk-3.3}/nltk/tokenize/stanford.py +117 -113
  347. nltk-3.3/nltk/tokenize/stanford_segmenter.py +246 -0
  348. {nltk-3.2 → nltk-3.3}/nltk/tokenize/texttiling.py +458 -460
  349. nltk-3.3/nltk/tokenize/toktok.py +155 -0
  350. nltk-3.3/nltk/tokenize/treebank.py +363 -0
  351. nltk-3.3/nltk/tokenize/util.py +261 -0
  352. {nltk-3.2 → nltk-3.3}/nltk/toolbox.py +499 -497
  353. {nltk-3.2 → nltk-3.3}/nltk/translate/__init__.py +24 -24
  354. {nltk-3.2 → nltk-3.3}/nltk/translate/api.py +331 -321
  355. {nltk-3.2 → nltk-3.3}/nltk/translate/bleu_score.py +615 -556
  356. nltk-3.3/nltk/translate/chrf_score.py +137 -0
  357. {nltk-3.2 → nltk-3.3}/nltk/translate/gale_church.py +248 -235
  358. {nltk-3.2 → nltk-3.3}/nltk/translate/gdfa.py +135 -131
  359. nltk-3.3/nltk/translate/gleu_score.py +193 -0
  360. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm1.py +250 -241
  361. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm2.py +308 -308
  362. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm3.py +337 -337
  363. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm4.py +467 -467
  364. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm5.py +639 -639
  365. {nltk-3.2 → nltk-3.3}/nltk/translate/ibm_model.py +536 -533
  366. {nltk-3.2 → nltk-3.3}/nltk/translate/metrics.py +40 -40
  367. nltk-3.3/nltk/translate/nist_score.py +178 -0
  368. {nltk-3.2 → nltk-3.3}/nltk/translate/phrase_based.py +175 -175
  369. {nltk-3.2 → nltk-3.3}/nltk/translate/ribes_score.py +325 -325
  370. {nltk-3.2 → nltk-3.3}/nltk/translate/stack_decoder.py +499 -495
  371. {nltk-3.2 → nltk-3.3}/nltk/tree.py +1605 -1603
  372. {nltk-3.2 → nltk-3.3}/nltk/treeprettyprinter.py +564 -564
  373. {nltk-3.2 → nltk-3.3}/nltk/treetransforms.py +309 -309
  374. {nltk-3.2 → nltk-3.3}/nltk/twitter/__init__.py +28 -28
  375. {nltk-3.2 → nltk-3.3}/nltk/twitter/api.py +141 -136
  376. {nltk-3.2 → nltk-3.3}/nltk/twitter/common.py +264 -258
  377. {nltk-3.2 → nltk-3.3}/nltk/twitter/twitter_demo.py +288 -288
  378. {nltk-3.2 → nltk-3.3}/nltk/twitter/twitterclient.py +530 -530
  379. {nltk-3.2 → nltk-3.3}/nltk/twitter/util.py +147 -146
  380. nltk-3.3/nltk/util.py +751 -0
  381. {nltk-3.2 → nltk-3.3}/nltk/wsd.py +53 -53
  382. {nltk-3.2 → nltk-3.3/nltk.egg-info}/PKG-INFO +13 -5
  383. {nltk-3.2 → nltk-3.3}/nltk.egg-info/SOURCES.txt +26 -3
  384. nltk-3.3/nltk.egg-info/requires.txt +31 -0
  385. {nltk-3.2 → nltk-3.3}/setup.cfg +0 -1
  386. {nltk-3.2 → nltk-3.3}/setup.py +102 -75
  387. nltk-3.2/nltk/VERSION +0 -1
  388. nltk-3.2/nltk/compat.py +0 -680
  389. nltk-3.2/nltk/corpus/reader/pl196x.py +0 -278
  390. nltk-3.2/nltk/corpus/reader/verbnet.py +0 -408
  391. nltk-3.2/nltk/corpus/reader/wordlist.py +0 -37
  392. nltk-3.2/nltk/sentiment/vader_lexicon.txt +0 -7517
  393. nltk-3.2/nltk/six.py +0 -868
  394. nltk-3.2/nltk/stem/porter.py +0 -692
  395. nltk-3.2/nltk/test/unit/test_2x_compat.py +0 -26
  396. nltk-3.2/nltk/test/unit/test_stem.py +0 -36
  397. nltk-3.2/nltk/test/unit/test_tokenize.py +0 -23
  398. nltk-3.2/nltk/test/unit/translate/test_bleu.py +0 -84
  399. nltk-3.2/nltk/tokenize/treebank.py +0 -124
  400. nltk-3.2/nltk/tokenize/util.py +0 -90
  401. nltk-3.2/nltk/util.py +0 -1364
  402. {nltk-3.2 → nltk-3.3}/nltk/test/unit/__init__.py +0 -0
  403. {nltk-3.2 → nltk-3.3}/nltk/test/unit/translate/__init__.py +0 -0
  404. {nltk-3.2 → nltk-3.3}/nltk.egg-info/dependency_links.txt +0 -0
  405. {nltk-3.2 → nltk-3.3}/nltk.egg-info/not-zip-safe +0 -0
  406. {nltk-3.2 → nltk-3.3}/nltk.egg-info/top_level.txt +0 -0
@@ -1,312 +1,343 @@
1
- # Natural Language Toolkit: Combinatory Categorial Grammar
2
- #
3
- # Copyright (C) 2001-2015 NLTK Project
4
- # Author: Graeme Gange <ggange@csse.unimelb.edu.au>
5
- # URL: <http://nltk.org/>
6
- # For license information, see LICENSE.TXT
7
- """
8
- CCG Combinators
9
- """
10
-
11
- from __future__ import unicode_literals
12
-
13
- from nltk.compat import python_2_unicode_compatible
14
- from nltk.ccg.api import FunctionalCategory
15
-
16
- class UndirectedBinaryCombinator(object):
17
- """
18
- Abstract class for representing a binary combinator.
19
- Merely defines functions for checking if the function and argument
20
- are able to be combined, and what the resulting category is.
21
-
22
- Note that as no assumptions are made as to direction, the unrestricted
23
- combinators can perform all backward, forward and crossed variations
24
- of the combinators; these restrictions must be added in the rule
25
- class.
26
- """
27
- def can_combine(self, function, argument):
28
- raise NotImplementedError()
29
-
30
- def combine (self, function, argument):
31
- raise NotImplementedError()
32
-
33
- class DirectedBinaryCombinator(object):
34
- """
35
- Wrapper for the undirected binary combinator.
36
- It takes left and right categories, and decides which is to be
37
- the function, and which the argument.
38
- It then decides whether or not they can be combined.
39
- """
40
- def can_combine(self, left, right):
41
- raise NotImplementedError()
42
-
43
- def combine(self, left, right):
44
- raise NotImplementedError()
45
-
46
- @python_2_unicode_compatible
47
- class ForwardCombinator(DirectedBinaryCombinator):
48
- """
49
- Class representing combinators where the primary functor is on the left.
50
-
51
- Takes an undirected combinator, and a predicate which adds constraints
52
- restricting the cases in which it may apply.
53
- """
54
- def __init__(self, combinator, predicate, suffix=''):
55
- self._combinator = combinator
56
- self._predicate = predicate
57
- self._suffix = suffix
58
-
59
- def can_combine(self, left, right):
60
- return (self._combinator.can_combine(left, right) and
61
- self._predicate(left, right))
62
-
63
- def combine(self, left, right):
64
- for cat in self._combinator.combine(left, right):
65
- yield cat
66
-
67
- def __str__(self):
68
- return ">%s%s" % (self._combinator, self._suffix)
69
-
70
- @python_2_unicode_compatible
71
- class BackwardCombinator(DirectedBinaryCombinator):
72
- """
73
- The backward equivalent of the ForwardCombinator class.
74
- """
75
- def __init__(self, combinator, predicate, suffix=''):
76
- self._combinator = combinator
77
- self._predicate = predicate
78
- self._suffix = suffix
79
-
80
- def can_combine(self, left, right):
81
- return (self._combinator.can_combine(right, left) and
82
- self._predicate(left, right))
83
- def combine(self, left, right):
84
- for cat in self._combinator.combine(right, left):
85
- yield cat
86
-
87
- def __str__(self):
88
- return "<%s%s" % (self._combinator, self._suffix)
89
-
90
- @python_2_unicode_compatible
91
- class UndirectedFunctionApplication(UndirectedBinaryCombinator):
92
- """
93
- Class representing function application.
94
- Implements rules of the form:
95
- X/Y Y -> X (>)
96
- And the corresponding backwards application rule
97
- """
98
-
99
- def can_combine(self, function, argument):
100
- if not function.is_function():
101
- return False
102
-
103
- return not function.arg().can_unify(argument) is None
104
-
105
- def combine(self, function, argument):
106
- if not function.is_function():
107
- return
108
-
109
- subs = function.arg().can_unify(argument)
110
- if subs is None:
111
- return
112
-
113
- yield function.res().substitute(subs)
114
-
115
- def __str__(self):
116
- return ''
117
-
118
-
119
- # Predicates for function application.
120
-
121
- # Ensures the left functor takes an argument on the right
122
- def forwardOnly(left, right):
123
- return left.dir().is_forward()
124
-
125
- # Ensures the right functor takes an argument on the left
126
- def backwardOnly(left, right):
127
- return right.dir().is_backward()
128
-
129
- # Application combinator instances
130
- ForwardApplication = ForwardCombinator(UndirectedFunctionApplication(),
131
- forwardOnly)
132
- BackwardApplication = BackwardCombinator(UndirectedFunctionApplication(),
133
- backwardOnly)
134
-
135
-
136
- @python_2_unicode_compatible
137
- class UndirectedComposition(UndirectedBinaryCombinator):
138
- """
139
- Functional composition (harmonic) combinator.
140
- Implements rules of the form
141
- X/Y Y/Z -> X/Z (B>)
142
- And the corresponding backwards and crossed variations.
143
- """
144
- def can_combine(self, function, argument):
145
- # Can only combine two functions, and both functions must
146
- # allow composition.
147
- if not (function.is_function() and argument.is_function()):
148
- return False
149
- if function.dir().can_compose() and argument.dir().can_compose():
150
- return not function.arg().can_unify(argument.res()) is None
151
- return False
152
-
153
- def combine(self, function, argument):
154
- if not (function.is_function() and argument.is_function()):
155
- return
156
- if function.dir().can_compose() and argument.dir().can_compose():
157
- subs = function.arg().can_unify(argument.res())
158
- if not subs is None:
159
- yield FunctionalCategory(function.res().substitute(subs),
160
- argument.arg().substitute(subs), argument.dir())
161
-
162
- def __str__(self):
163
- return 'B'
164
-
165
- # Predicates for restricting application of straight composition.
166
- def bothForward(left, right):
167
- return left.dir().is_forward() and right.dir().is_forward()
168
-
169
- def bothBackward(left, right):
170
- return left.dir().is_backward() and right.dir().is_backward()
171
-
172
- # Predicates for crossed composition
173
-
174
- def crossedDirs(left, right):
175
- return left.dir().is_forward() and right.dir().is_backward()
176
-
177
- def backwardBxConstraint(left, right):
178
- # The functors must be crossed inwards
179
- if not crossedDirs(left, right):
180
- return False
181
- # Permuting combinators must be allowed
182
- if not left.dir().can_cross() and right.dir().can_cross():
183
- return False
184
- # The resulting argument category is restricted to be primitive
185
- return left.arg().is_primitive()
186
-
187
- # Straight composition combinators
188
- ForwardComposition = ForwardCombinator(UndirectedComposition(),
189
- forwardOnly)
190
- BackwardComposition = BackwardCombinator(UndirectedComposition(),
191
- backwardOnly)
192
-
193
- # Backward crossed composition
194
- BackwardBx = BackwardCombinator(UndirectedComposition(), backwardBxConstraint,
195
- suffix='x')
196
-
197
- @python_2_unicode_compatible
198
- class UndirectedSubstitution(UndirectedBinaryCombinator):
199
- """
200
- Substitution (permutation) combinator.
201
- Implements rules of the form
202
- Y/Z (X\Y)/Z -> X/Z (<Sx)
203
- And other variations.
204
- """
205
- def can_combine(self, function, argument):
206
- if function.is_primitive() or argument.is_primitive():
207
- return False
208
-
209
- # These could potentially be moved to the predicates, as the
210
- # constraints may not be general to all languages.
211
- if function.res().is_primitive():
212
- return False
213
- if not function.arg().is_primitive():
214
- return False
215
-
216
- if not (function.dir().can_compose() and argument.dir().can_compose()):
217
- return False
218
- return (function.res().arg() == argument.res()) and (function.arg() == argument.arg())
219
-
220
- def combine(self, function, argument):
221
- if self.can_combine(function, argument):
222
- yield FunctionalCategory(function.res().res(), argument.arg(), argument.dir())
223
-
224
- def __str__(self):
225
- return 'S'
226
-
227
- # Predicate for forward substitution
228
- def forwardSConstraint(left, right):
229
- if not bothForward(left, right):
230
- return False
231
- return left.res().dir().is_forward() and left.arg().is_primitive()
232
-
233
- # Predicate for backward crossed substitution
234
- def backwardSxConstraint(left, right):
235
- if not left.dir().can_cross() and right.dir().can_cross():
236
- return False
237
- if not bothForward(left, right):
238
- return False
239
- return right.res().dir().is_backward() and right.arg().is_primitive()
240
-
241
- # Instances of substitution combinators
242
- ForwardSubstitution = ForwardCombinator(UndirectedSubstitution(),
243
- forwardSConstraint)
244
- BackwardSx = BackwardCombinator(UndirectedSubstitution(),
245
- backwardSxConstraint, 'x')
246
-
247
-
248
- # Retrieves the left-most functional category.
249
- # ie, (N\N)/(S/NP) => N\N
250
- def innermostFunction(categ):
251
- while categ.res().is_function():
252
- categ = categ.res()
253
- return categ
254
-
255
- @python_2_unicode_compatible
256
- class UndirectedTypeRaise(UndirectedBinaryCombinator):
257
- """
258
- Undirected combinator for type raising.
259
- """
260
- def can_combine(self, function, arg):
261
- # The argument must be a function.
262
- # The restriction that arg.res() must be a function
263
- # merely reduces redundant type-raising; if arg.res() is
264
- # primitive, we have:
265
- # X Y\X =>(<T) Y/(Y\X) Y\X =>(>) Y
266
- # which is equivalent to
267
- # X Y\X =>(<) Y
268
- if not (arg.is_function() and arg.res().is_function()):
269
- return False
270
-
271
- arg = innermostFunction(arg)
272
-
273
- # left, arg_categ are undefined!
274
- subs = left.can_unify(arg_categ.arg())
275
- if subs is not None:
276
- return True
277
- return False
278
-
279
- def combine(self, function, arg):
280
- if not (function.is_primitive() and
281
- arg.is_function() and arg.res().is_function()):
282
- return
283
-
284
- # Type-raising matches only the innermost application.
285
- arg = innermostFunction(arg)
286
-
287
- subs = function.can_unify(arg.arg())
288
- if subs is not None:
289
- xcat = arg.res().substitute(subs)
290
- yield FunctionalCategory(xcat,
291
- FunctionalCategory(xcat, function, arg.dir()),
292
- -(arg.dir()))
293
-
294
- def __str__(self):
295
- return 'T'
296
-
297
- # Predicates for type-raising
298
- # The direction of the innermost category must be towards
299
- # the primary functor.
300
- # The restriction that the variable must be primitive is not
301
- # common to all versions of CCGs; some authors have other restrictions.
302
- def forwardTConstraint(left, right):
303
- arg = innermostFunction(right)
304
- return arg.dir().is_backward() and arg.res().is_primitive()
305
-
306
- def backwardTConstraint(left, right):
307
- arg = innermostFunction(left)
308
- return arg.dir().is_forward() and arg.res().is_primitive()
309
-
310
- # Instances of type-raising combinators
311
- ForwardT = ForwardCombinator(UndirectedTypeRaise(), forwardTConstraint)
312
- BackwardT = BackwardCombinator(UndirectedTypeRaise(), backwardTConstraint)
1
+ # Natural Language Toolkit: Combinatory Categorial Grammar
2
+ #
3
+ # Copyright (C) 2001-2018 NLTK Project
4
+ # Author: Graeme Gange <ggange@csse.unimelb.edu.au>
5
+ # URL: <http://nltk.org/>
6
+ # For license information, see LICENSE.TXT
7
+ """
8
+ CCG Combinators
9
+ """
10
+
11
+ from __future__ import unicode_literals
12
+ from abc import ABCMeta, abstractmethod
13
+ from six import add_metaclass
14
+
15
+ from nltk.compat import python_2_unicode_compatible
16
+ from nltk.ccg.api import FunctionalCategory
17
+
18
+
19
+ @add_metaclass(ABCMeta)
20
+ class UndirectedBinaryCombinator(object):
21
+ """
22
+ Abstract class for representing a binary combinator.
23
+ Merely defines functions for checking if the function and argument
24
+ are able to be combined, and what the resulting category is.
25
+
26
+ Note that as no assumptions are made as to direction, the unrestricted
27
+ combinators can perform all backward, forward and crossed variations
28
+ of the combinators; these restrictions must be added in the rule
29
+ class.
30
+ """
31
+ @abstractmethod
32
+ def can_combine(self, function, argument):
33
+ pass
34
+
35
+ @abstractmethod
36
+ def combine(self, function, argument):
37
+ pass
38
+
39
+
40
+ @add_metaclass(ABCMeta)
41
+ class DirectedBinaryCombinator(object):
42
+ """
43
+ Wrapper for the undirected binary combinator.
44
+ It takes left and right categories, and decides which is to be
45
+ the function, and which the argument.
46
+ It then decides whether or not they can be combined.
47
+ """
48
+ @abstractmethod
49
+ def can_combine(self, left, right):
50
+ pass
51
+
52
+ @abstractmethod
53
+ def combine(self, left, right):
54
+ pass
55
+
56
+
57
+ @python_2_unicode_compatible
58
+ class ForwardCombinator(DirectedBinaryCombinator):
59
+ """
60
+ Class representing combinators where the primary functor is on the left.
61
+
62
+ Takes an undirected combinator, and a predicate which adds constraints
63
+ restricting the cases in which it may apply.
64
+ """
65
+ def __init__(self, combinator, predicate, suffix=''):
66
+ self._combinator = combinator
67
+ self._predicate = predicate
68
+ self._suffix = suffix
69
+
70
+ def can_combine(self, left, right):
71
+ return (self._combinator.can_combine(left, right) and
72
+ self._predicate(left, right))
73
+
74
+ def combine(self, left, right):
75
+ for cat in self._combinator.combine(left, right):
76
+ yield cat
77
+
78
+ def __str__(self):
79
+ return ">%s%s" % (self._combinator, self._suffix)
80
+
81
+
82
+ @python_2_unicode_compatible
83
+ class BackwardCombinator(DirectedBinaryCombinator):
84
+ """
85
+ The backward equivalent of the ForwardCombinator class.
86
+ """
87
+ def __init__(self, combinator, predicate, suffix=''):
88
+ self._combinator = combinator
89
+ self._predicate = predicate
90
+ self._suffix = suffix
91
+
92
+ def can_combine(self, left, right):
93
+ return (self._combinator.can_combine(right, left) and
94
+ self._predicate(left, right))
95
+
96
+ def combine(self, left, right):
97
+ for cat in self._combinator.combine(right, left):
98
+ yield cat
99
+
100
+ def __str__(self):
101
+ return "<%s%s" % (self._combinator, self._suffix)
102
+
103
+
104
+ @python_2_unicode_compatible
105
+ class UndirectedFunctionApplication(UndirectedBinaryCombinator):
106
+ """
107
+ Class representing function application.
108
+ Implements rules of the form:
109
+ X/Y Y -> X (>)
110
+ And the corresponding backwards application rule
111
+ """
112
+
113
+ def can_combine(self, function, argument):
114
+ if not function.is_function():
115
+ return False
116
+
117
+ return not function.arg().can_unify(argument) is None
118
+
119
+ def combine(self, function, argument):
120
+ if not function.is_function():
121
+ return
122
+
123
+ subs = function.arg().can_unify(argument)
124
+ if subs is None:
125
+ return
126
+
127
+ yield function.res().substitute(subs)
128
+
129
+ def __str__(self):
130
+ return ''
131
+
132
+
133
+ # Predicates for function application.
134
+
135
+ # Ensures the left functor takes an argument on the right
136
+ def forwardOnly(left, right):
137
+ return left.dir().is_forward()
138
+
139
+
140
+ # Ensures the right functor takes an argument on the left
141
+ def backwardOnly(left, right):
142
+ return right.dir().is_backward()
143
+
144
+
145
+ # Application combinator instances
146
+ ForwardApplication = ForwardCombinator(UndirectedFunctionApplication(),
147
+ forwardOnly)
148
+ BackwardApplication = BackwardCombinator(UndirectedFunctionApplication(),
149
+ backwardOnly)
150
+
151
+
152
+ @python_2_unicode_compatible
153
+ class UndirectedComposition(UndirectedBinaryCombinator):
154
+ """
155
+ Functional composition (harmonic) combinator.
156
+ Implements rules of the form
157
+ X/Y Y/Z -> X/Z (B>)
158
+ And the corresponding backwards and crossed variations.
159
+ """
160
+ def can_combine(self, function, argument):
161
+ # Can only combine two functions, and both functions must
162
+ # allow composition.
163
+ if not (function.is_function() and argument.is_function()):
164
+ return False
165
+ if function.dir().can_compose() and argument.dir().can_compose():
166
+ return not function.arg().can_unify(argument.res()) is None
167
+ return False
168
+
169
+ def combine(self, function, argument):
170
+ if not (function.is_function() and argument.is_function()):
171
+ return
172
+ if function.dir().can_compose() and argument.dir().can_compose():
173
+ subs = function.arg().can_unify(argument.res())
174
+ if subs is not None:
175
+ yield FunctionalCategory(function.res().substitute(subs),
176
+ argument.arg().substitute(subs),
177
+ argument.dir())
178
+
179
+ def __str__(self):
180
+ return 'B'
181
+
182
+
183
+ # Predicates for restricting application of straight composition.
184
+ def bothForward(left, right):
185
+ return left.dir().is_forward() and right.dir().is_forward()
186
+
187
+
188
+ def bothBackward(left, right):
189
+ return left.dir().is_backward() and right.dir().is_backward()
190
+
191
+
192
+ # Predicates for crossed composition
193
+ def crossedDirs(left, right):
194
+ return left.dir().is_forward() and right.dir().is_backward()
195
+
196
+
197
+ def backwardBxConstraint(left, right):
198
+ # The functors must be crossed inwards
199
+ if not crossedDirs(left, right):
200
+ return False
201
+ # Permuting combinators must be allowed
202
+ if not left.dir().can_cross() and right.dir().can_cross():
203
+ return False
204
+ # The resulting argument category is restricted to be primitive
205
+ return left.arg().is_primitive()
206
+
207
+
208
+ # Straight composition combinators
209
+ ForwardComposition = ForwardCombinator(UndirectedComposition(),
210
+ forwardOnly)
211
+ BackwardComposition = BackwardCombinator(UndirectedComposition(),
212
+ backwardOnly)
213
+
214
+ # Backward crossed composition
215
+ BackwardBx = BackwardCombinator(UndirectedComposition(), backwardBxConstraint,
216
+ suffix='x')
217
+
218
+
219
+ @python_2_unicode_compatible
220
+ class UndirectedSubstitution(UndirectedBinaryCombinator):
221
+ """
222
+ Substitution (permutation) combinator.
223
+ Implements rules of the form
224
+ Y/Z (X\Y)/Z -> X/Z (<Sx)
225
+ And other variations.
226
+ """
227
+ def can_combine(self, function, argument):
228
+ if function.is_primitive() or argument.is_primitive():
229
+ return False
230
+
231
+ # These could potentially be moved to the predicates, as the
232
+ # constraints may not be general to all languages.
233
+ if function.res().is_primitive():
234
+ return False
235
+ if not function.arg().is_primitive():
236
+ return False
237
+
238
+ if not (function.dir().can_compose() and argument.dir().can_compose()):
239
+ return False
240
+ return (function.res().arg() == argument.res()) and (function.arg() == argument.arg())
241
+
242
+ def combine(self, function, argument):
243
+ if self.can_combine(function, argument):
244
+ yield FunctionalCategory(function.res().res(), argument.arg(),
245
+ argument.dir())
246
+
247
+ def __str__(self):
248
+ return 'S'
249
+
250
+
251
+ # Predicate for forward substitution
252
+ def forwardSConstraint(left, right):
253
+ if not bothForward(left, right):
254
+ return False
255
+ return left.res().dir().is_forward() and left.arg().is_primitive()
256
+
257
+
258
+ # Predicate for backward crossed substitution
259
+ def backwardSxConstraint(left, right):
260
+ if not left.dir().can_cross() and right.dir().can_cross():
261
+ return False
262
+ if not bothForward(left, right):
263
+ return False
264
+ return right.res().dir().is_backward() and right.arg().is_primitive()
265
+
266
+
267
+ # Instances of substitution combinators
268
+ ForwardSubstitution = ForwardCombinator(UndirectedSubstitution(),
269
+ forwardSConstraint)
270
+ BackwardSx = BackwardCombinator(UndirectedSubstitution(),
271
+ backwardSxConstraint, 'x')
272
+
273
+
274
+ # Retrieves the left-most functional category.
275
+ # ie, (N\N)/(S/NP) => N\N
276
+ def innermostFunction(categ):
277
+ while categ.res().is_function():
278
+ categ = categ.res()
279
+ return categ
280
+
281
+
282
+ @python_2_unicode_compatible
283
+ class UndirectedTypeRaise(UndirectedBinaryCombinator):
284
+ """
285
+ Undirected combinator for type raising.
286
+ """
287
+ def can_combine(self, function, arg):
288
+ # The argument must be a function.
289
+ # The restriction that arg.res() must be a function
290
+ # merely reduces redundant type-raising; if arg.res() is
291
+ # primitive, we have:
292
+ # X Y\X =>(<T) Y/(Y\X) Y\X =>(>) Y
293
+ # which is equivalent to
294
+ # X Y\X =>(<) Y
295
+ if not (arg.is_function() and arg.res().is_function()):
296
+ return False
297
+
298
+ arg = innermostFunction(arg)
299
+
300
+ # left, arg_categ are undefined!
301
+ subs = left.can_unify(arg_categ.arg())
302
+ if subs is not None:
303
+ return True
304
+ return False
305
+
306
+ def combine(self, function, arg):
307
+ if not (function.is_primitive() and
308
+ arg.is_function() and arg.res().is_function()):
309
+ return
310
+
311
+ # Type-raising matches only the innermost application.
312
+ arg = innermostFunction(arg)
313
+
314
+ subs = function.can_unify(arg.arg())
315
+ if subs is not None:
316
+ xcat = arg.res().substitute(subs)
317
+ yield FunctionalCategory(xcat,
318
+ FunctionalCategory(xcat, function,
319
+ arg.dir()),
320
+ -(arg.dir()))
321
+
322
+ def __str__(self):
323
+ return 'T'
324
+
325
+
326
+ # Predicates for type-raising
327
+ # The direction of the innermost category must be towards
328
+ # the primary functor.
329
+ # The restriction that the variable must be primitive is not
330
+ # common to all versions of CCGs; some authors have other restrictions.
331
+ def forwardTConstraint(left, right):
332
+ arg = innermostFunction(right)
333
+ return arg.dir().is_backward() and arg.res().is_primitive()
334
+
335
+
336
+ def backwardTConstraint(left, right):
337
+ arg = innermostFunction(left)
338
+ return arg.dir().is_forward() and arg.res().is_primitive()
339
+
340
+
341
+ # Instances of type-raising combinators
342
+ ForwardT = ForwardCombinator(UndirectedTypeRaise(), forwardTConstraint)
343
+ BackwardT = BackwardCombinator(UndirectedTypeRaise(), backwardTConstraint)