■
英語の形態素解析機器GENIA tagger
実行はインストールしたフォルダで,
./geniatagger Alice.txt
処理にすごく時間がかかる.
不思議の国のアリスの冒頭「Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do:」はこんな感じ.
元の単語,原型(base),品詞(POStag),チャンク(chunk),NE(Named Entity)
Alice Alice NNP B-NP O was be VBD B-VP O beginning begin VBG I-VP O to to TO I-VP O get get VB I-VP O very very RB B-ADJP O tired tired JJ I-ADJP O of of IN B-PP O sitting sit VBG B-VP O by by IN B-PP O her her PRP$ B-NP O sister sister NN I-NP O on on IN B-PP O the the DT B-NP O bank bank NN B-NP O , , , B-PP O and and CC I-PP O of of IN B-PP O having have VBG B-VP O nothing nothing NN B-NP O to to TO B-VP O do do VB I-VP O : : : O O
他にも,Brill's TaggerやTreeTagger(フランス,スペイン可能)があるとのこと.