Japanese semantic role labeling with hierarchical tag context trees

Yasuhiro Ishihara, Koichi Takeuchi

研究成果

抄録

In this paper we describe that the hierarchical tag context tree (HTCT) approach improves the accuracy of semantic role labeling on Japanese text. In Japanese language there are functional multiword expressions such as no-tame-ni and yotte that have potential to designate semantic relations between a predicate and its arguments. Since these expressions come to the end part of each argument, the performance of the CRF-based semantic role labeler can be improved by taking into account the last morphemes of each argument as features. We apply our proposed system to the annotated corpus of semantic role labels on a balanced Japanese corpus. The experimental results show that the CRFbased labeler with features extracted by HTCT approach outperforms the normal CRF-based labeler.

本文言語English
ホスト出版物のタイトルComputational Linguistics - 14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015, Revised Selected Papers
編集者Koiti Hasida, Ayu Purwarianti
出版社Springer Verlag
ページ21-32
ページ数12
ISBN(印刷版)9789811005145
DOI
出版ステータスPublished - 2016
イベント14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015 - Bali
継続期間: 5月 19 20155月 21 2015

出版物シリーズ

名前Communications in Computer and Information Science
593
ISSN(印刷版)1865-0929

Other

Other14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015
国/地域Indonesia
CityBali
Period5/19/155/21/15

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 数学 (全般)

フィンガープリント

「Japanese semantic role labeling with hierarchical tag context trees」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル