natural 0.2.1 → 0.4.0
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.
- package/.npmignore +4 -11
- package/README.md +156 -41
- package/bayes_classifier.json +1 -0
- package/lib/natural/brill_pos_tagger/data/Dutch/README.txt +2 -0
- package/lib/natural/brill_pos_tagger/data/Dutch/brill_CONTEXTRULES.jg +285 -0
- package/lib/natural/brill_pos_tagger/data/Dutch/brill_LEXICON.jg +11699 -0
- package/lib/natural/brill_pos_tagger/data/English/README.txt +8 -0
- package/lib/natural/brill_pos_tagger/data/English/lexicon_from_posjs.json +297827 -0
- package/lib/natural/brill_pos_tagger/data/English/tr_from_brill_paper.txt +10 -0
- package/lib/natural/brill_pos_tagger/data/English/tr_from_posjs.txt +18 -0
- package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js +136 -0
- package/lib/natural/brill_pos_tagger/lib/Predicate.js +410 -0
- package/lib/natural/brill_pos_tagger/lib/TF_Parser.js +717 -0
- package/lib/natural/brill_pos_tagger/lib/TF_Parser.pegjs +55 -0
- package/lib/natural/brill_pos_tagger/lib/TransformationRule.js +49 -0
- package/lib/natural/classifiers/bayes_classifier.js +6 -5
- package/lib/natural/classifiers/classifier.js +3 -2
- package/lib/natural/classifiers/logistic_regression_classifier.js +9 -5
- package/lib/natural/distance/dice_coefficient.js +22 -12
- package/lib/natural/index.js +6 -0
- package/lib/natural/ngrams/ngrams.js +4 -0
- package/lib/natural/stemmers/stemmer.js +31 -6
- package/lib/natural/tokenizers/regexp_tokenizer.js +3 -3
- package/{examples/inflection/noun.js → lib/natural/tokenizers/sentence_tokenizer.js} +14 -10
- package/lib/natural/tokenizers/tokenizer_case.js +58 -0
- package/lib/natural/util/bag.js +1 -0
- package/lib/natural/wordnet/wordnet.js +2 -2
- package/lib/natural/wordnet/wordnet_file.js +1 -1
- package/lr_classifier.json +1 -0
- package/package.json +6 -3
- package/package.json~ +66 -0
- package/benchmarks/index.js +0 -32
- package/benchmarks/metaphone.js +0 -27
- package/benchmarks/soundex.js +0 -27
- package/examples/classification/basic.js +0 -35
- package/examples/classification/recall.js +0 -28
- package/examples/classification/store.js +0 -37
- package/examples/inflection/count.js +0 -35
- package/examples/inflection/noun_attach.js +0 -33
- package/examples/phonetics/compare.js +0 -39
- package/examples/phonetics/sounds_like.js +0 -40
- package/examples/phonetics/tokenize_and_phoneticize.js +0 -54
- package/examples/stemming/stem_corpus.js +0 -29
- package/examples/stemming/stem_word.js +0 -26
- package/examples/tfidf/array_example.js +0 -34
- package/examples/tfidf/multiple_terms.js +0 -33
- package/examples/tfidf/tfidf_example.js +0 -44
- package/io_spec/test_data/tfidf/one +0 -1
- package/io_spec/test_data/tfidf/two +0 -1
- package/io_spec/tfidf_spec.js +0 -50
- package/io_spec/wordnet_spec.js +0 -81
- package/spec/aggressive_tokenizer_es_spec.js +0 -36
- package/spec/aggressive_tokenizer_fr_spec.js +0 -101
- package/spec/aggressive_tokenizer_nl_spec.js +0 -36
- package/spec/aggressive_tokenizer_pt_spec.js +0 -56
- package/spec/aggressive_tokenizer_spec.js +0 -56
- package/spec/bayes_classifier_spec.js +0 -173
- package/spec/classifier_spec.js +0 -175
- package/spec/count_inflector_fr_spec.js +0 -44
- package/spec/count_inflector_spec.js +0 -73
- package/spec/dice_coefficient_spec.js +0 -26
- package/spec/double_metaphone_spec.js +0 -752
- package/spec/jaro-winkler_spec.js +0 -53
- package/spec/lancaster_stemmer_spec.js +0 -73
- package/spec/levenshtein_spec.js +0 -66
- package/spec/logistic_regression_classifier_spec.js +0 -122
- package/spec/longest_path_tree_spec.js +0 -102
- package/spec/metaphone_spec.js +0 -252
- package/spec/ngram_spec.js +0 -130
- package/spec/ngram_zh_spec.js +0 -122
- package/spec/normalizer_ja_spec.js +0 -160
- package/spec/normalizer_no_spec.js +0 -111
- package/spec/normalizer_spec.js +0 -140
- package/spec/noun_inflector_fr_spec.js +0 -476
- package/spec/noun_inflector_ja_spec.js +0 -112
- package/spec/noun_inflector_spec.js +0 -270
- package/spec/porter_stemmer_fr_spec.js +0 -101
- package/spec/porter_stemmer_it_spec.js +0 -44
- package/spec/porter_stemmer_no_spec.js +0 -143
- package/spec/porter_stemmer_pt_spec.js +0 -50
- package/spec/porter_stemmer_ru_spec.js +0 -63
- package/spec/porter_stemmer_spec.js +0 -182
- package/spec/present_verb_inflector_spec.js +0 -128
- package/spec/remove_diacritics_spec.js +0 -31
- package/spec/sentence_analyzer_spec.js +0 -277
- package/spec/shortest_path_tree_spec.js +0 -132
- package/spec/soundex_spec.js +0 -158
- package/spec/spellcheck_spec.js +0 -92
- package/spec/stemmer_ja_spec.js +0 -66
- package/spec/stemmer_token_spec.js +0 -161
- package/spec/test_data/snowball_fr.txt +0 -20402
- package/spec/test_data/snowball_it.txt +0 -35482
- package/spec/test_data/snowball_no.txt +0 -20628
- package/spec/test_data/snowball_pt.txt +0 -32016
- package/spec/test_data/tfdif_testcorpus.txt +0 -7
- package/spec/test_data/tfidf_document1.txt +0 -1
- package/spec/test_data/tfidf_document2.txt +0 -1
- package/spec/test_data/tfidf_document3.txt +0 -1
- package/spec/test_data/tfidf_document4.txt +0 -1
- package/spec/test_data/tfidf_teststopwords.txt +0 -1
- package/spec/test_data/wordnet_mini.sql +0 -95
- package/spec/tfidf_spec.js +0 -323
- package/spec/tokenizer_ja_spec.js +0 -58
- package/spec/transliterator_ja_spec.js +0 -103
- package/spec/treebank_word_tokenizer_spec.js +0 -36
- package/spec/trie_spec.js +0 -206
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
The tranformation rules in tr_from_brill_paper.txt are from this article:
|
|
2
|
+
A simple rule-based part of speech tagger, Eric Brill, Published in: Proceeding ANLC '92 Proceedings of the third conference on Applied natural language processing, Pages 152-155. http://dl.acm.org/citation.cfm?id=974526
|
|
3
|
+
|
|
4
|
+
The lexicon in lexicon_from_posjs.json is from:
|
|
5
|
+
https://github.com/dariusk/pos-js
|
|
6
|
+
|
|
7
|
+
The transformation rules in tr_from_posj.txt are derived from Javascript code in:
|
|
8
|
+
BrillTransformationRules.js from https://github.com/dariusk/pos-js/
|