Cross-lingual knowledge projection using machine translation and target-side knowledge base completion

Naoki Otani*, Hirokazu Kiyomaru, Daisuke Kawahara, Sadao Kurohashi

*この研究の対応する著者

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

Considerable effort has been devoted to building commonsense knowledge bases. However, they are not available in many languages because the construction of KBs is expensive. To bridge the gap between languages, this paper addresses the problem of projecting the knowledge in English, a resource-rich language, into other languages, where the main challenge lies in projection ambiguity. This ambiguity is partially solved by machine translation and target-side knowledge base completion, but neither of them is adequately reliable by itself. We show their combination can project English commonsense knowledge into Japanese and Chinese with high precision. Our method also achieves a top-10 accuracy of 90% on the crowdsourced English–Japanese benchmark. Furthermore, we use our method to obtain 18,747 facts of accurate Japanese commonsense within a very short period.

本文言語English
ホスト出版物のタイトルCOLING 2018 - 27th International Conference on Computational Linguistics, Proceedings
編集者Emily M. Bender, Leon Derczynski, Pierre Isabelle
出版社Association for Computational Linguistics (ACL)
ページ1508-1520
ページ数13
ISBN(電子版)9781948087506
出版ステータスPublished - 2018
外部発表はい
イベント27th International Conference on Computational Linguistics, COLING 2018 - Santa Fe, United States
継続期間: 2018 8月 202018 8月 26

出版物シリーズ

名前COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings

Conference

Conference27th International Conference on Computational Linguistics, COLING 2018
国/地域United States
CitySanta Fe
Period18/8/2018/8/26

ASJC Scopus subject areas

  • 言語および言語学
  • 計算理論と計算数学
  • 言語学および言語

フィンガープリント

「Cross-lingual knowledge projection using machine translation and target-side knowledge base completion」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