Reinventing Part-Of-Speech Tagging

この論文にアクセスする

この論文をさがす

著者

抄録

Part-of-speech tagging methodology has succeeded, but on problems that may lack real-world application. Redirection of the field is indicated, toward potentially more useful, but harder and more sophisticated tagging tasks: (1) using much more detailed tagsets (semantically <I>and</I> syntactically); (2) testing performance on treebanks reflecting the huge gamut of domains, etc., characterizing real-world applications; (3) understanding the magnitude of the unknown-word and unknown-tag problems, then overcoming them. Tagging results are presented on two versions of a new, highly variegated treebank, featuring tagsets of 2720 and 443 tags, respectively, and utilizing a dictionaryless, decision-tree tagger.

収録刊行物

  • 自然言語処理 = Journal of natural language processing

    自然言語処理 = Journal of natural language processing 5(1), 3-23, 1998-01-10

    一般社団法人 言語処理学会

参考文献:  20件中 1-20件 を表示

被引用文献:  1件中 1-1件 を表示

各種コード

  • NII論文ID(NAID)
    10008827415
  • NII書誌ID(NCID)
    AN10472659
  • 本文言語コード
    ENG
  • 資料種別
    ART
  • ISSN
    13407619
  • データ提供元
    CJP書誌  CJP引用  J-STAGE 
ページトップへ