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
{nltk-3.2 → nltk-3.3}/nltk/test/ccg.doctest RENAMED
@@ -1,395 +1,376 @@
1
- .. Copyright (C) 2001-2015 NLTK Project
2
- .. For license information, see LICENSE.TXT
3
-
4
- ==============================
5
- Combinatory Categorial Grammar
6
- ==============================
7
-
8
- Relative Clauses
9
- ----------------
10
-
11
- >>> from nltk.ccg import chart, lexicon
12
-
13
- Construct a lexicon:
14
-
15
- >>> lex = lexicon.parseLexicon('''
16
- ... :- S, NP, N, VP
17
- ...
18
- ... Det :: NP/N
19
- ... Pro :: NP
20
- ... Modal :: S\\NP/VP
21
- ...
22
- ... TV :: VP/NP
23
- ... DTV :: TV/NP
24
- ...
25
- ... the => Det
26
- ...
27
- ... that => Det
28
- ... that => NP
29
- ...
30
- ... I => Pro
31
- ... you => Pro
32
- ... we => Pro
33
- ...
34
- ... chef => N
35
- ... cake => N
36
- ... children => N
37
- ... dough => N
38
- ...
39
- ... will => Modal
40
- ... should => Modal
41
- ... might => Modal
42
- ... must => Modal
43
- ...
44
- ... and => var\\.,var/.,var
45
- ...
46
- ... to => VP[to]/VP
47
- ...
48
- ... without => (VP\\VP)/VP[ing]
49
- ...
50
- ... be => TV
51
- ... cook => TV
52
- ... eat => TV
53
- ...
54
- ... cooking => VP[ing]/NP
55
- ...
56
- ... give => DTV
57
- ...
58
- ... is => (S\\NP)/NP
59
- ... prefer => (S\\NP)/NP
60
- ...
61
- ... which => (N\\N)/(S/NP)
62
- ...
63
- ... persuade => (VP/VP[to])/NP
64
- ... ''')
65
-
66
- >>> parser = chart.CCGChartParser(lex, chart.DefaultRuleSet)
67
- >>> for parse in parser.parse("you prefer that cake".split()): # doctest: +SKIP
68
- ... chart.printCCGDerivation(parse)
69
- ... break
70
- ...
71
- you prefer that cake
72
- NP ((S\NP)/NP) (NP/N) N
73
- -------------->
74
- NP
75
- --------------------------->
76
- (S\NP)
77
- --------------------------------<
78
- S
79
-
80
- >>> for parse in parser.parse("that is the cake which you prefer".split()): # doctest: +SKIP
81
- ... chart.printCCGDerivation(parse)
82
- ... break
83
- ...
84
- that is the cake which you prefer
85
- NP ((S\NP)/NP) (NP/N) N ((N\N)/(S/NP)) NP ((S\NP)/NP)
86
- ----->T
87
- (S/(S\NP))
88
- ------------------>B
89
- (S/NP)
90
- ---------------------------------->
91
- (N\N)
92
- ----------------------------------------<
93
- N
94
- ------------------------------------------------>
95
- NP
96
- ------------------------------------------------------------->
97
- (S\NP)
98
- -------------------------------------------------------------------<
99
- S
100
-
101
-
102
- Some other sentences to try:
103
- "that is the cake which we will persuade the chef to cook"
104
- "that is the cake which we will persuade the chef to give the children"
105
-
106
- >>> sent = "that is the dough which you will eat without cooking".split()
107
- >>> nosub_parser = chart.CCGChartParser(lex, chart.ApplicationRuleSet +
108
- ... chart.CompositionRuleSet + chart.TypeRaiseRuleSet)
109
-
110
- Without Substitution (no output)
111
-
112
- >>> for parse in nosub_parser.parse(sent):
113
- ... chart.printCCGDerivation(parse)
114
-
115
- With Substitution:
116
-
117
- >>> for parse in parser.parse(sent): # doctest: +SKIP
118
- ... chart.printCCGDerivation(parse)
119
- ... break
120
- ...
121
- that is the dough which you will eat without cooking
122
- NP ((S\NP)/NP) (NP/N) N ((N\N)/(S/NP)) NP ((S\NP)/VP) (VP/NP) ((VP\VP)/VP['ing']) (VP['ing']/NP)
123
- ----->T
124
- (S/(S\NP))
125
- ------------------------------------->B
126
- ((VP\VP)/NP)
127
- ----------------------------------------------<Sx
128
- (VP/NP)
129
- ----------------------------------------------------------->B
130
- ((S\NP)/NP)
131
- ---------------------------------------------------------------->B
132
- (S/NP)
133
- -------------------------------------------------------------------------------->
134
- (N\N)
135
- ---------------------------------------------------------------------------------------<
136
- N
137
- ----------------------------------------------------------------------------------------------->
138
- NP
139
- ------------------------------------------------------------------------------------------------------------>
140
- (S\NP)
141
- ------------------------------------------------------------------------------------------------------------------<
142
- S
143
-
144
-
145
- Conjunction
146
- -----------
147
-
148
- >>> from nltk.ccg.chart import CCGChartParser, ApplicationRuleSet, CompositionRuleSet
149
- >>> from nltk.ccg.chart import SubstitutionRuleSet, TypeRaiseRuleSet, printCCGDerivation
150
- >>> from nltk.ccg import lexicon
151
-
152
- Lexicons for the tests:
153
-
154
- >>> test1_lex = '''
155
- ... :- S,N,NP,VP
156
- ... I => NP
157
- ... you => NP
158
- ... will => S\\NP/VP
159
- ... cook => VP/NP
160
- ... which => (N\\N)/(S/NP)
161
- ... and => var\\.,var/.,var
162
- ... might => S\\NP/VP
163
- ... eat => VP/NP
164
- ... the => NP/N
165
- ... mushrooms => N
166
- ... parsnips => N'''
167
- >>> test2_lex = '''
168
- ... :- N, S, NP, VP
169
- ... articles => N
170
- ... the => NP/N
171
- ... and => var\\.,var/.,var
172
- ... which => (N\\N)/(S/NP)
173
- ... I => NP
174
- ... anyone => NP
175
- ... will => (S/VP)\\NP
176
- ... file => VP/NP
177
- ... without => (VP\\VP)/VP[ing]
178
- ... forget => VP/NP
179
- ... reading => VP[ing]/NP
180
- ... '''
181
-
182
- Tests handling of conjunctions.
183
- Note that while the two derivations are different, they are semantically equivalent.
184
-
185
- >>> lex = lexicon.parseLexicon(test1_lex)
186
- >>> parser = CCGChartParser(lex, ApplicationRuleSet + CompositionRuleSet + SubstitutionRuleSet)
187
- >>> for parse in parser.parse("I will cook and might eat the mushrooms and parsnips".split()):
188
- ... printCCGDerivation(parse) # doctest: +NORMALIZE_WHITESPACE +SKIP
189
- I will cook and might eat the mushrooms and parsnips
190
- NP ((S\NP)/VP) (VP/NP) ((_var2\.,_var2)/.,_var2) ((S\NP)/VP) (VP/NP) (NP/N) N ((_var2\.,_var2)/.,_var2) N
191
- ---------------------->B
192
- ((S\NP)/NP)
193
- ---------------------->B
194
- ((S\NP)/NP)
195
- ------------------------------------------------->
196
- (((S\NP)/NP)\.,((S\NP)/NP))
197
- -----------------------------------------------------------------------<
198
- ((S\NP)/NP)
199
- ------------------------------------->
200
- (N\.,N)
201
- ------------------------------------------------<
202
- N
203
- -------------------------------------------------------->
204
- NP
205
- ------------------------------------------------------------------------------------------------------------------------------->
206
- (S\NP)
207
- -----------------------------------------------------------------------------------------------------------------------------------<
208
- S
209
- I will cook and might eat the mushrooms and parsnips
210
- NP ((S\NP)/VP) (VP/NP) ((_var2\.,_var2)/.,_var2) ((S\NP)/VP) (VP/NP) (NP/N) N ((_var2\.,_var2)/.,_var2) N
211
- ---------------------->B
212
- ((S\NP)/NP)
213
- ---------------------->B
214
- ((S\NP)/NP)
215
- ------------------------------------------------->
216
- (((S\NP)/NP)\.,((S\NP)/NP))
217
- -----------------------------------------------------------------------<
218
- ((S\NP)/NP)
219
- ------------------------------------------------------------------------------->B
220
- ((S\NP)/N)
221
- ------------------------------------->
222
- (N\.,N)
223
- ------------------------------------------------<
224
- N
225
- ------------------------------------------------------------------------------------------------------------------------------->
226
- (S\NP)
227
- -----------------------------------------------------------------------------------------------------------------------------------<
228
- S
229
-
230
-
231
- Tests handling subject extraction.
232
- Interesting to point that the two parses are clearly semantically different.
233
-
234
- >>> lex = lexicon.parseLexicon(test2_lex)
235
- >>> parser = CCGChartParser(lex, ApplicationRuleSet + CompositionRuleSet + SubstitutionRuleSet)
236
- >>> for parse in parser.parse("articles which I will file and forget without reading".split()):
237
- ... printCCGDerivation(parse) # doctest: +NORMALIZE_WHITESPACE +SKIP
238
- articles which I will file and forget without reading
239
- N ((N\N)/(S/NP)) NP ((S/VP)\NP) (VP/NP) ((_var3\.,_var3)/.,_var3) (VP/NP) ((VP\VP)/VP['ing']) (VP['ing']/NP)
240
- -----------------<
241
- (S/VP)
242
- ------------------------------------->B
243
- ((VP\VP)/NP)
244
- ----------------------------------------------<Sx
245
- (VP/NP)
246
- ------------------------------------------------------------------------->
247
- ((VP/NP)\.,(VP/NP))
248
- ----------------------------------------------------------------------------------<
249
- (VP/NP)
250
- --------------------------------------------------------------------------------------------------->B
251
- (S/NP)
252
- ------------------------------------------------------------------------------------------------------------------->
253
- (N\N)
254
- -----------------------------------------------------------------------------------------------------------------------------<
255
- N
256
- articles which I will file and forget without reading
257
- N ((N\N)/(S/NP)) NP ((S/VP)\NP) (VP/NP) ((_var3\.,_var3)/.,_var3) (VP/NP) ((VP\VP)/VP['ing']) (VP['ing']/NP)
258
- -----------------<
259
- (S/VP)
260
- ------------------------------------>
261
- ((VP/NP)\.,(VP/NP))
262
- ---------------------------------------------<
263
- (VP/NP)
264
- ------------------------------------->B
265
- ((VP\VP)/NP)
266
- ----------------------------------------------------------------------------------<Sx
267
- (VP/NP)
268
- --------------------------------------------------------------------------------------------------->B
269
- (S/NP)
270
- ------------------------------------------------------------------------------------------------------------------->
271
- (N\N)
272
- -----------------------------------------------------------------------------------------------------------------------------<
273
- N
274
-
275
-
276
- Unicode support
277
- ---------------
278
-
279
- Unicode words are supported.
280
-
281
- >>> from nltk.ccg import chart, lexicon
282
-
283
- Lexicons for the tests:
284
-
285
- >>> lex = lexicon.parseLexicon(u'''
286
- ... :- S, N, NP, PP
287
- ...
288
- ... AdjI :: N\\N
289
- ... AdjD :: N/N
290
- ... AdvD :: S/S
291
- ... AdvI :: S\\S
292
- ... Det :: NP/N
293
- ... PrepNPCompl :: PP/NP
294
- ... PrepNAdjN :: S\\S/N
295
- ... PrepNAdjNP :: S\\S/NP
296
- ... VPNP :: S\\NP/NP
297
- ... VPPP :: S\\NP/PP
298
- ... VPser :: S\\NP/AdjI
299
- ...
300
- ... auto => N
301
- ... bebidas => N
302
- ... cine => N
303
- ... ley => N
304
- ... libro => N
305
- ... ministro => N
306
- ... panadería => N
307
- ... presidente => N
308
- ... super => N
309
- ...
310
- ... el => Det
311
- ... la => Det
312
- ... las => Det
313
- ... un => Det
314
- ...
315
- ... Ana => NP
316
- ... Pablo => NP
317
- ...
318
- ... y => var\\.,var/.,var
319
- ...
320
- ... pero => (S/NP)\\(S/NP)/(S/NP)
321
- ...
322
- ... anunció => VPNP
323
- ... compró => VPNP
324
- ... cree => S\\NP/S[dep]
325
- ... desmintió => VPNP
326
- ... lee => VPNP
327
- ... fueron => VPPP
328
- ...
329
- ... es => VPser
330
- ...
331
- ... interesante => AdjD
332
- ... interesante => AdjI
333
- ... nueva => AdjD
334
- ... nueva => AdjI
335
- ...
336
- ... a => PrepNPCompl
337
- ... en => PrepNAdjN
338
- ... en => PrepNAdjNP
339
- ...
340
- ... ayer => AdvI
341
- ...
342
- ... que => (NP\\NP)/(S/NP)
343
- ... que => S[dep]/S
344
- ... ''')
345
-
346
- >>> parser = chart.CCGChartParser(lex, chart.DefaultRuleSet)
347
- >>> for parse in parser.parse(u"el ministro anunció pero el presidente desmintió la nueva ley".split()):
348
- ... printCCGDerivation(parse) # doctest: +NORMALIZE_WHITESPACE
349
- ... break
350
- el ministro anunció pero el presidente desmintió la nueva ley
351
- (NP/N) N ((S\NP)/NP) (((S/NP)\(S/NP))/(S/NP)) (NP/N) N ((S\NP)/NP) (NP/N) (N/N) N
352
- --------Leaf
353
- (NP/N)
354
- ----------Leaf
355
- N
356
- ------------------>
357
- NP
358
- ------------------>T
359
- (S/(S\NP))
360
- -------------Leaf
361
- ((S\NP)/NP)
362
- --------------------------Leaf
363
- (((S/NP)\(S/NP))/(S/NP))
364
- --------Leaf
365
- (NP/N)
366
- ------------Leaf
367
- N
368
- -------------------->
369
- NP
370
- -------------------->T
371
- (S/(S\NP))
372
- -------------Leaf
373
- ((S\NP)/NP)
374
- --------------------------------->B
375
- (S/NP)
376
- ----------------------------------------------------------->
377
- ((S/NP)\(S/NP))
378
- --------Leaf
379
- (NP/N)
380
- -------Leaf
381
- (N/N)
382
- -----Leaf
383
- N
384
- ------------>
385
- N
386
- -------------------->
387
- NP
388
- --------------------<T
389
- (S\(S/NP))
390
- -------------------------------------------------------------------------------<B
391
- (S\(S/NP))
392
- --------------------------------------------------------------------------------------------<B
393
- (S/NP)
394
- -------------------------------------------------------------------------------------------------------------->
395
- S
1
+ .. Copyright (C) 2001-2018 NLTK Project
2
+ .. For license information, see LICENSE.TXT
3
+
4
+ ==============================
5
+ Combinatory Categorial Grammar
6
+ ==============================
7
+
8
+ Relative Clauses
9
+ ----------------
10
+
11
+ >>> from nltk.ccg import chart, lexicon
12
+
13
+ Construct a lexicon:
14
+
15
+ >>> lex = lexicon.parseLexicon('''
16
+ ... :- S, NP, N, VP
17
+ ...
18
+ ... Det :: NP/N
19
+ ... Pro :: NP
20
+ ... Modal :: S\\NP/VP
21
+ ...
22
+ ... TV :: VP/NP
23
+ ... DTV :: TV/NP
24
+ ...
25
+ ... the => Det
26
+ ...
27
+ ... that => Det
28
+ ... that => NP
29
+ ...
30
+ ... I => Pro
31
+ ... you => Pro
32
+ ... we => Pro
33
+ ...
34
+ ... chef => N
35
+ ... cake => N
36
+ ... children => N
37
+ ... dough => N
38
+ ...
39
+ ... will => Modal
40
+ ... should => Modal
41
+ ... might => Modal
42
+ ... must => Modal
43
+ ...
44
+ ... and => var\\.,var/.,var
45
+ ...
46
+ ... to => VP[to]/VP
47
+ ...
48
+ ... without => (VP\\VP)/VP[ing]
49
+ ...
50
+ ... be => TV
51
+ ... cook => TV
52
+ ... eat => TV
53
+ ...
54
+ ... cooking => VP[ing]/NP
55
+ ...
56
+ ... give => DTV
57
+ ...
58
+ ... is => (S\\NP)/NP
59
+ ... prefer => (S\\NP)/NP
60
+ ...
61
+ ... which => (N\\N)/(S/NP)
62
+ ...
63
+ ... persuade => (VP/VP[to])/NP
64
+ ... ''')
65
+
66
+ >>> parser = chart.CCGChartParser(lex, chart.DefaultRuleSet)
67
+ >>> for parse in parser.parse("you prefer that cake".split()):
68
+ ... chart.printCCGDerivation(parse)
69
+ ... break
70
+ ...
71
+ you prefer that cake
72
+ NP ((S\NP)/NP) (NP/N) N
73
+ -------------->
74
+ NP
75
+ --------------------------->
76
+ (S\NP)
77
+ --------------------------------<
78
+ S
79
+
80
+ >>> for parse in parser.parse("that is the cake which you prefer".split()):
81
+ ... chart.printCCGDerivation(parse)
82
+ ... break
83
+ ...
84
+ that is the cake which you prefer
85
+ NP ((S\NP)/NP) (NP/N) N ((N\N)/(S/NP)) NP ((S\NP)/NP)
86
+ ----->T
87
+ (S/(S\NP))
88
+ ------------------>B
89
+ (S/NP)
90
+ ---------------------------------->
91
+ (N\N)
92
+ ----------------------------------------<
93
+ N
94
+ ------------------------------------------------>
95
+ NP
96
+ ------------------------------------------------------------->
97
+ (S\NP)
98
+ -------------------------------------------------------------------<
99
+ S
100
+
101
+
102
+ Some other sentences to try:
103
+ "that is the cake which we will persuade the chef to cook"
104
+ "that is the cake which we will persuade the chef to give the children"
105
+
106
+ >>> sent = "that is the dough which you will eat without cooking".split()
107
+ >>> nosub_parser = chart.CCGChartParser(lex, chart.ApplicationRuleSet +
108
+ ... chart.CompositionRuleSet + chart.TypeRaiseRuleSet)
109
+
110
+ Without Substitution (no output)
111
+
112
+ >>> for parse in nosub_parser.parse(sent):
113
+ ... chart.printCCGDerivation(parse)
114
+
115
+ With Substitution:
116
+
117
+ >>> for parse in parser.parse(sent):
118
+ ... chart.printCCGDerivation(parse)
119
+ ... break
120
+ ...
121
+ that is the dough which you will eat without cooking
122
+ NP ((S\NP)/NP) (NP/N) N ((N\N)/(S/NP)) NP ((S\NP)/VP) (VP/NP) ((VP\VP)/VP['ing']) (VP['ing']/NP)
123
+ ----->T
124
+ (S/(S\NP))
125
+ ------------------------------------->B
126
+ ((VP\VP)/NP)
127
+ ----------------------------------------------<Sx
128
+ (VP/NP)
129
+ ----------------------------------------------------------->B
130
+ ((S\NP)/NP)
131
+ ---------------------------------------------------------------->B
132
+ (S/NP)
133
+ -------------------------------------------------------------------------------->
134
+ (N\N)
135
+ ---------------------------------------------------------------------------------------<
136
+ N
137
+ ----------------------------------------------------------------------------------------------->
138
+ NP
139
+ ------------------------------------------------------------------------------------------------------------>
140
+ (S\NP)
141
+ ------------------------------------------------------------------------------------------------------------------<
142
+ S
143
+
144
+
145
+ Conjunction
146
+ -----------
147
+
148
+ >>> from nltk.ccg.chart import CCGChartParser, ApplicationRuleSet, CompositionRuleSet
149
+ >>> from nltk.ccg.chart import SubstitutionRuleSet, TypeRaiseRuleSet, printCCGDerivation
150
+ >>> from nltk.ccg import lexicon
151
+
152
+ Lexicons for the tests:
153
+
154
+ >>> test1_lex = '''
155
+ ... :- S,N,NP,VP
156
+ ... I => NP
157
+ ... you => NP
158
+ ... will => S\\NP/VP
159
+ ... cook => VP/NP
160
+ ... which => (N\\N)/(S/NP)
161
+ ... and => var\\.,var/.,var
162
+ ... might => S\\NP/VP
163
+ ... eat => VP/NP
164
+ ... the => NP/N
165
+ ... mushrooms => N
166
+ ... parsnips => N'''
167
+ >>> test2_lex = '''
168
+ ... :- N, S, NP, VP
169
+ ... articles => N
170
+ ... the => NP/N
171
+ ... and => var\\.,var/.,var
172
+ ... which => (N\\N)/(S/NP)
173
+ ... I => NP
174
+ ... anyone => NP
175
+ ... will => (S/VP)\\NP
176
+ ... file => VP/NP
177
+ ... without => (VP\\VP)/VP[ing]
178
+ ... forget => VP/NP
179
+ ... reading => VP[ing]/NP
180
+ ... '''
181
+
182
+ Tests handling of conjunctions.
183
+ Note that while the two derivations are different, they are semantically equivalent.
184
+
185
+ >>> lex = lexicon.parseLexicon(test1_lex)
186
+ >>> parser = CCGChartParser(lex, ApplicationRuleSet + CompositionRuleSet + SubstitutionRuleSet)
187
+ >>> for parse in parser.parse("I will cook and might eat the mushrooms and parsnips".split()):
188
+ ... printCCGDerivation(parse)
189
+ I will cook and might eat the mushrooms and parsnips
190
+ NP ((S\NP)/VP) (VP/NP) ((_var0\.,_var0)/.,_var0) ((S\NP)/VP) (VP/NP) (NP/N) N ((_var0\.,_var0)/.,_var0) N
191
+ ---------------------->B
192
+ ((S\NP)/NP)
193
+ ---------------------->B
194
+ ((S\NP)/NP)
195
+ ------------------------------------------------->
196
+ (((S\NP)/NP)\.,((S\NP)/NP))
197
+ -----------------------------------------------------------------------<
198
+ ((S\NP)/NP)
199
+ ------------------------------------->
200
+ (N\.,N)
201
+ ------------------------------------------------<
202
+ N
203
+ -------------------------------------------------------->
204
+ NP
205
+ ------------------------------------------------------------------------------------------------------------------------------->
206
+ (S\NP)
207
+ -----------------------------------------------------------------------------------------------------------------------------------<
208
+ S
209
+ I will cook and might eat the mushrooms and parsnips
210
+ NP ((S\NP)/VP) (VP/NP) ((_var0\.,_var0)/.,_var0) ((S\NP)/VP) (VP/NP) (NP/N) N ((_var0\.,_var0)/.,_var0) N
211
+ ---------------------->B
212
+ ((S\NP)/NP)
213
+ ---------------------->B
214
+ ((S\NP)/NP)
215
+ ------------------------------------------------->
216
+ (((S\NP)/NP)\.,((S\NP)/NP))
217
+ -----------------------------------------------------------------------<
218
+ ((S\NP)/NP)
219
+ ------------------------------------------------------------------------------->B
220
+ ((S\NP)/N)
221
+ ------------------------------------->
222
+ (N\.,N)
223
+ ------------------------------------------------<
224
+ N
225
+ ------------------------------------------------------------------------------------------------------------------------------->
226
+ (S\NP)
227
+ -----------------------------------------------------------------------------------------------------------------------------------<
228
+ S
229
+
230
+
231
+ Tests handling subject extraction.
232
+ Interesting to point that the two parses are clearly semantically different.
233
+
234
+ >>> lex = lexicon.parseLexicon(test2_lex)
235
+ >>> parser = CCGChartParser(lex, ApplicationRuleSet + CompositionRuleSet + SubstitutionRuleSet)
236
+ >>> for parse in parser.parse("articles which I will file and forget without reading".split()):
237
+ ... printCCGDerivation(parse)
238
+ articles which I will file and forget without reading
239
+ N ((N\N)/(S/NP)) NP ((S/VP)\NP) (VP/NP) ((_var0\.,_var0)/.,_var0) (VP/NP) ((VP\VP)/VP['ing']) (VP['ing']/NP)
240
+ -----------------<
241
+ (S/VP)
242
+ ------------------------------------->B
243
+ ((VP\VP)/NP)
244
+ ----------------------------------------------<Sx
245
+ (VP/NP)
246
+ ------------------------------------------------------------------------->
247
+ ((VP/NP)\.,(VP/NP))
248
+ ----------------------------------------------------------------------------------<
249
+ (VP/NP)
250
+ --------------------------------------------------------------------------------------------------->B
251
+ (S/NP)
252
+ ------------------------------------------------------------------------------------------------------------------->
253
+ (N\N)
254
+ -----------------------------------------------------------------------------------------------------------------------------<
255
+ N
256
+ articles which I will file and forget without reading
257
+ N ((N\N)/(S/NP)) NP ((S/VP)\NP) (VP/NP) ((_var0\.,_var0)/.,_var0) (VP/NP) ((VP\VP)/VP['ing']) (VP['ing']/NP)
258
+ -----------------<
259
+ (S/VP)
260
+ ------------------------------------>
261
+ ((VP/NP)\.,(VP/NP))
262
+ ---------------------------------------------<
263
+ (VP/NP)
264
+ ------------------------------------->B
265
+ ((VP\VP)/NP)
266
+ ----------------------------------------------------------------------------------<Sx
267
+ (VP/NP)
268
+ --------------------------------------------------------------------------------------------------->B
269
+ (S/NP)
270
+ ------------------------------------------------------------------------------------------------------------------->
271
+ (N\N)
272
+ -----------------------------------------------------------------------------------------------------------------------------<
273
+ N
274
+
275
+
276
+ Unicode support
277
+ ---------------
278
+
279
+ Unicode words are supported.
280
+
281
+ >>> from nltk.ccg import chart, lexicon
282
+
283
+ Lexicons for the tests:
284
+
285
+ >>> lex = lexicon.parseLexicon(u'''
286
+ ... :- S, N, NP, PP
287
+ ...
288
+ ... AdjI :: N\\N
289
+ ... AdjD :: N/N
290
+ ... AdvD :: S/S
291
+ ... AdvI :: S\\S
292
+ ... Det :: NP/N
293
+ ... PrepNPCompl :: PP/NP
294
+ ... PrepNAdjN :: S\\S/N
295
+ ... PrepNAdjNP :: S\\S/NP
296
+ ... VPNP :: S\\NP/NP
297
+ ... VPPP :: S\\NP/PP
298
+ ... VPser :: S\\NP/AdjI
299
+ ...
300
+ ... auto => N
301
+ ... bebidas => N
302
+ ... cine => N
303
+ ... ley => N
304
+ ... libro => N
305
+ ... ministro => N
306
+ ... panadería => N
307
+ ... presidente => N
308
+ ... super => N
309
+ ...
310
+ ... el => Det
311
+ ... la => Det
312
+ ... las => Det
313
+ ... un => Det
314
+ ...
315
+ ... Ana => NP
316
+ ... Pablo => NP
317
+ ...
318
+ ... y => var\\.,var/.,var
319
+ ...
320
+ ... pero => (S/NP)\\(S/NP)/(S/NP)
321
+ ...
322
+ ... anunció => VPNP
323
+ ... compró => VPNP
324
+ ... cree => S\\NP/S[dep]
325
+ ... desmintió => VPNP
326
+ ... lee => VPNP
327
+ ... fueron => VPPP
328
+ ...
329
+ ... es => VPser
330
+ ...
331
+ ... interesante => AdjD
332
+ ... interesante => AdjI
333
+ ... nueva => AdjD
334
+ ... nueva => AdjI
335
+ ...
336
+ ... a => PrepNPCompl
337
+ ... en => PrepNAdjN
338
+ ... en => PrepNAdjNP
339
+ ...
340
+ ... ayer => AdvI
341
+ ...
342
+ ... que => (NP\\NP)/(S/NP)
343
+ ... que => S[dep]/S
344
+ ... ''')
345
+
346
+ >>> parser = chart.CCGChartParser(lex, chart.DefaultRuleSet)
347
+ >>> for parse in parser.parse(u"el ministro anunció pero el presidente desmintió la nueva ley".split()):
348
+ ... printCCGDerivation(parse) # doctest: +SKIP
349
+ ... # it fails on python2.7 because of the unicode problem explained in https://github.com/nltk/nltk/pull/1354
350
+ ... break
351
+ el ministro anunció pero el presidente desmintió la nueva ley
352
+ (NP/N) N ((S\NP)/NP) (((S/NP)\(S/NP))/(S/NP)) (NP/N) N ((S\NP)/NP) (NP/N) (N/N) N
353
+ ------------------>
354
+ NP
355
+ ------------------>T
356
+ (S/(S\NP))
357
+ -------------------->
358
+ NP
359
+ -------------------->T
360
+ (S/(S\NP))
361
+ --------------------------------->B
362
+ (S/NP)
363
+ ----------------------------------------------------------->
364
+ ((S/NP)\(S/NP))
365
+ ------------>
366
+ N
367
+ -------------------->
368
+ NP
369
+ --------------------<T
370
+ (S\(S/NP))
371
+ -------------------------------------------------------------------------------<B
372
+ (S\(S/NP))
373
+ --------------------------------------------------------------------------------------------<B
374
+ (S/NP)
375
+ -------------------------------------------------------------------------------------------------------------->
376
+ S