README.md
setup.cfg
setup.py
versioneer.py
autophrase/.DS_Store
autophrase/Makefile
autophrase/__init__.py
autophrase/_version.py
autophrase/auto_phrase.sh
autophrase/autophrase.py
autophrase/compile.sh
autophrase/phrasal_segmentation.sh
autophrase/pos_tag.py
autophrase/test.py
autophrase/wiki_url.py
autophrase.egg-info/PKG-INFO
autophrase.egg-info/SOURCES.txt
autophrase.egg-info/dependency_links.txt
autophrase.egg-info/top_level.txt
autophrase/__pycache__/__init__.cpython-38.pyc
autophrase/__pycache__/_version.cpython-38.pyc
autophrase/__pycache__/autophrase.cpython-38.pyc
autophrase/__pycache__/pos_tag.cpython-38.pyc
autophrase/__pycache__/wiki_url.cpython-38.pyc
autophrase/bin/segphrase_segment
autophrase/bin/segphrase_train
autophrase/data/BAD_POS_TAGS.txt
autophrase/data/CN/paper.txt
autophrase/data/CN/stopwords.txt
autophrase/data/CN/wiki_all.txt
autophrase/data/CN/wiki_quality.txt
autophrase/data/EN/DBLP.5K.txt
autophrase/data/EN/stopwords.txt
autophrase/data/EN/wiki_all.txt
autophrase/data/EN/wiki_quality.txt
autophrase/data/ErrTest/test.txt
autophrase/data/JA/stopwords.txt
autophrase/data/JA/wiki_all.txt
autophrase/data/JA/wiki_quality.txt
autophrase/docker/Dockerfile
autophrase/docker/make.sh
autophrase/src/.DS_Store
autophrase/src/main.cpp
autophrase/src/segment.cpp
autophrase/src/classification/feature_extraction.h
autophrase/src/classification/label_generation.h
autophrase/src/classification/predict_quality.h
autophrase/src/classification/random_forest.h
autophrase/src/clustering/clustering.h
autophrase/src/data/documents.h
autophrase/src/data/dump.h
autophrase/src/frequent_pattern_mining/frequent_pattern_mining.h
autophrase/src/model_training/segmentation.h
autophrase/src/utils/commandline_flags.h
autophrase/src/utils/parameters.h
autophrase/src/utils/random.h
autophrase/src/utils/utils.h
autophrase/tmp/case_tokenized_train.txt
autophrase/tmp/language.txt
autophrase/tmp/pos_tags_tokenized_train.txt
autophrase/tmp/raw_tokenized_all.txt
autophrase/tmp/raw_tokenized_quality.txt
autophrase/tmp/raw_tokenized_stopwords.txt
autophrase/tmp/token_mapping.txt
autophrase/tmp/tokenized_all.txt
autophrase/tmp/tokenized_quality.txt
autophrase/tmp/tokenized_stopwords.txt
autophrase/tmp/tokenized_train.txt
autophrase/tools/models/arabic.tagger
autophrase/tools/tokenizer/.DS_Store
autophrase/tools/tokenizer/.gitignore
autophrase/tools/tokenizer/build.xml
autophrase/tools/tokenizer/readme(tokenizer).txt
autophrase/tools/tokenizer/build/ArabicTagger.class
autophrase/tools/tokenizer/build/ChineseTagger.class
autophrase/tools/tokenizer/build/SpecialTagger.class
autophrase/tools/tokenizer/build/StandardTagger.class
autophrase/tools/tokenizer/build/Tokenizer$1.class
autophrase/tools/tokenizer/build/Tokenizer$Output.class
autophrase/tools/tokenizer/build/Tokenizer.class
autophrase/tools/tokenizer/lib/ansj_seg-5.0.2-all-in-one.jar
autophrase/tools/tokenizer/lib/jsonic-1.2.0.jar
autophrase/tools/tokenizer/lib/langdetect.jar
autophrase/tools/tokenizer/lib/lucene-analyzers-common-5.2.0.jar
autophrase/tools/tokenizer/lib/lucene-analyzers-kuromoji-5.4.0.jar
autophrase/tools/tokenizer/lib/lucene-analyzers-smartcn-5.4.0.jar
autophrase/tools/tokenizer/lib/lucene-core-5.4.0.jar
autophrase/tools/tokenizer/lib/slf4j-api.jar
autophrase/tools/tokenizer/lib/slf4j-simple.jar
autophrase/tools/tokenizer/lib/stanford-corenlp-3.8.0.jar
autophrase/tools/tokenizer/resources/cjk_punctuation_mapping.txt
autophrase/tools/tokenizer/resources/indo_european_punctuation_mapping.txt
autophrase/tools/tokenizer/resources/profiles.sm/ar
autophrase/tools/tokenizer/resources/profiles.sm/bg
autophrase/tools/tokenizer/resources/profiles.sm/bn
autophrase/tools/tokenizer/resources/profiles.sm/ca
autophrase/tools/tokenizer/resources/profiles.sm/cs
autophrase/tools/tokenizer/resources/profiles.sm/da
autophrase/tools/tokenizer/resources/profiles.sm/de
autophrase/tools/tokenizer/resources/profiles.sm/el
autophrase/tools/tokenizer/resources/profiles.sm/en
autophrase/tools/tokenizer/resources/profiles.sm/es
autophrase/tools/tokenizer/resources/profiles.sm/et
autophrase/tools/tokenizer/resources/profiles.sm/fa
autophrase/tools/tokenizer/resources/profiles.sm/fi
autophrase/tools/tokenizer/resources/profiles.sm/fr
autophrase/tools/tokenizer/resources/profiles.sm/gu
autophrase/tools/tokenizer/resources/profiles.sm/he
autophrase/tools/tokenizer/resources/profiles.sm/hi
autophrase/tools/tokenizer/resources/profiles.sm/hr
autophrase/tools/tokenizer/resources/profiles.sm/hu
autophrase/tools/tokenizer/resources/profiles.sm/id
autophrase/tools/tokenizer/resources/profiles.sm/it
autophrase/tools/tokenizer/resources/profiles.sm/ja
autophrase/tools/tokenizer/resources/profiles.sm/ko
autophrase/tools/tokenizer/resources/profiles.sm/lt
autophrase/tools/tokenizer/resources/profiles.sm/lv
autophrase/tools/tokenizer/resources/profiles.sm/mk
autophrase/tools/tokenizer/resources/profiles.sm/ml
autophrase/tools/tokenizer/resources/profiles.sm/nl
autophrase/tools/tokenizer/resources/profiles.sm/no
autophrase/tools/tokenizer/resources/profiles.sm/pa
autophrase/tools/tokenizer/resources/profiles.sm/pl
autophrase/tools/tokenizer/resources/profiles.sm/pt
autophrase/tools/tokenizer/resources/profiles.sm/ro
autophrase/tools/tokenizer/resources/profiles.sm/ru
autophrase/tools/tokenizer/resources/profiles.sm/si
autophrase/tools/tokenizer/resources/profiles.sm/sq
autophrase/tools/tokenizer/resources/profiles.sm/sv
autophrase/tools/tokenizer/resources/profiles.sm/ta
autophrase/tools/tokenizer/resources/profiles.sm/te
autophrase/tools/tokenizer/resources/profiles.sm/th
autophrase/tools/tokenizer/resources/profiles.sm/tl
autophrase/tools/tokenizer/resources/profiles.sm/tr
autophrase/tools/tokenizer/resources/profiles.sm/uk
autophrase/tools/tokenizer/resources/profiles.sm/ur
autophrase/tools/tokenizer/resources/profiles.sm/vi
autophrase/tools/tokenizer/resources/profiles.sm/zh-cn
autophrase/tools/tokenizer/resources/profiles.sm/zh-tw
autophrase/tools/tokenizer/src/Tokenizer.java
autophrase/tools/treetagger/.gitignore
autophrase/tools/treetagger/FILES
autophrase/tools/treetagger/LICENSE
autophrase/tools/treetagger/README
autophrase/tools/treetagger/README.script
autophrase/tools/treetagger/download_parameter_files.sh
autophrase/tools/treetagger/merge_tagged_files.py
autophrase/tools/treetagger/pos_tag.sh
autophrase/tools/treetagger/prepare_untagged_files.py
autophrase/tools/treetagger/bin/separate-punctuation
autophrase/tools/treetagger/bin/train-tree-tagger
autophrase/tools/treetagger/bin/tree-tagger
autophrase/tools/treetagger/bin/tree-tagger-flush
autophrase/tools/treetagger/bin/tree-tagger-linux
autophrase/tools/treetagger/bin/tree-tagger-linux-old
autophrase/tools/treetagger/bin/tree-tagger-mac
autophrase/tools/treetagger/cmd/#tagger-chunker-spanish#
autophrase/tools/treetagger/cmd/chinese-2c.utf8
autophrase/tools/treetagger/cmd/chinese-3c.utf8
autophrase/tools/treetagger/cmd/chunker-read-lemma.perl
autophrase/tools/treetagger/cmd/chunker-write-lemma.perl
autophrase/tools/treetagger/cmd/create-chunker-par-file
autophrase/tools/treetagger/cmd/create-pos-par-file
autophrase/tools/treetagger/cmd/filter-chunker-output-french.perl
autophrase/tools/treetagger/cmd/filter-chunker-output-german.perl
autophrase/tools/treetagger/cmd/filter-chunker-output.perl
autophrase/tools/treetagger/cmd/filter-coordinate-output.perl
autophrase/tools/treetagger/cmd/filter-german-tags
autophrase/tools/treetagger/cmd/lookup.perl
autophrase/tools/treetagger/cmd/make-chunk-lex.perl
autophrase/tools/treetagger/cmd/make-lex.perl
autophrase/tools/treetagger/cmd/mwl-lookup.perl
autophrase/tools/treetagger/cmd/portuguese-post-tagging
autophrase/tools/treetagger/cmd/portuguese-splitter.perl
autophrase/tools/treetagger/cmd/segment-zh.perl
autophrase/tools/treetagger/cmd/segmenter.pm
autophrase/tools/treetagger/cmd/split-romanian.perl
autophrase/tools/treetagger/cmd/tagger-chunker-english
autophrase/tools/treetagger/cmd/tagger-chunker-french
autophrase/tools/treetagger/cmd/tagger-chunker-german
autophrase/tools/treetagger/cmd/tagger-chunker-spanish
autophrase/tools/treetagger/cmd/tokenize.pl
autophrase/tools/treetagger/cmd/tree-tagger-bulgarian
autophrase/tools/treetagger/cmd/tree-tagger-chinese
autophrase/tools/treetagger/cmd/tree-tagger-dutch
autophrase/tools/treetagger/cmd/tree-tagger-english
autophrase/tools/treetagger/cmd/tree-tagger-estonian
autophrase/tools/treetagger/cmd/tree-tagger-finnish
autophrase/tools/treetagger/cmd/tree-tagger-french
autophrase/tools/treetagger/cmd/tree-tagger-galician
autophrase/tools/treetagger/cmd/tree-tagger-german
autophrase/tools/treetagger/cmd/tree-tagger-italian
autophrase/tools/treetagger/cmd/tree-tagger-latin
autophrase/tools/treetagger/cmd/tree-tagger-polish
autophrase/tools/treetagger/cmd/tree-tagger-portuguese
autophrase/tools/treetagger/cmd/tree-tagger-portuguese-finegrained
autophrase/tools/treetagger/cmd/tree-tagger-romanian
autophrase/tools/treetagger/cmd/tree-tagger-russian
autophrase/tools/treetagger/cmd/tree-tagger-slovak
autophrase/tools/treetagger/cmd/tree-tagger-slovenian
autophrase/tools/treetagger/cmd/tree-tagger-spanish
autophrase/tools/treetagger/cmd/tree-tagger-swahili
autophrase/tools/treetagger/cmd/utf8-tokenize.perl
autophrase/tools/treetagger/doc/nemlap94.ps
autophrase/tools/treetagger/doc/sigdat95.ps
autophrase/tools/treetagger/lib/bulgarian-abbreviations
autophrase/tools/treetagger/lib/bulgarian-mwls
autophrase/tools/treetagger/lib/dutch-abbreviations
autophrase/tools/treetagger/lib/english-abbreviations
autophrase/tools/treetagger/lib/english-utf8.par
autophrase/tools/treetagger/lib/estonian-abbreviations-utf8
autophrase/tools/treetagger/lib/estonian-mwls-utf8
autophrase/tools/treetagger/lib/finnish-abbreviations-utf8
autophrase/tools/treetagger/lib/french-abbreviations
autophrase/tools/treetagger/lib/french-abbreviations-utf8
autophrase/tools/treetagger/lib/galician-abbreviations-utf8
autophrase/tools/treetagger/lib/galician-mwls
autophrase/tools/treetagger/lib/german-abbreviations
autophrase/tools/treetagger/lib/german-abbreviations-utf8
autophrase/tools/treetagger/lib/german-lexicon-utf8.txt
autophrase/tools/treetagger/lib/german-lexicon.txt
autophrase/tools/treetagger/lib/italian-abbreviations
autophrase/tools/treetagger/lib/latin-abbreviations
autophrase/tools/treetagger/lib/latin-mwls
autophrase/tools/treetagger/lib/polish-abbreviations-utf8
autophrase/tools/treetagger/lib/portuguese-abbreviations-utf8
autophrase/tools/treetagger/lib/romanian-abbreviations
autophrase/tools/treetagger/lib/romanian-tokens
autophrase/tools/treetagger/lib/spanish-abbreviations
autophrase/tools/treetagger/lib/spanish-mwls
autophrase/tools/treetagger/lib/spanish-mwls-utf8
autophrase/tools/treetagger/lib/swahili-abbreviations