Joint learning of the embedding of words and entities for named entity disambiguation

Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji

研究成果: Conference contribution

125 被引用数 (Scopus)

抄録

Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in a document to their correct references in a knowledge base (KB) (e.g., Wikipedia). In this paper, we propose a novel embedding method specifically designed for NED. The proposed method jointly maps words and entities into the same continuous vector space. We extend the skip-gram model by using two models. The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words. By combining contexts based on the proposed embedding with standard NED features, we achieved state-of-the-art accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset.

本文言語English
ホスト出版物のタイトルCoNLL 2016 - 20th SIGNLL Conference on Computational Natural Language Learning, Proceedings
出版社Association for Computational Linguistics (ACL)
ページ250-259
ページ数10
ISBN(電子版)9781945626197
DOI
出版ステータスPublished - 2016
イベント20th SIGNLL Conference on Computational Natural Language Learning, CoNLL 2016 - Berlin, Germany
継続期間: 2016 8 112016 8 12

出版物シリーズ

名前CoNLL 2016 - 20th SIGNLL Conference on Computational Natural Language Learning, Proceedings

Conference

Conference20th SIGNLL Conference on Computational Natural Language Learning, CoNLL 2016
CountryGermany
CityBerlin
Period16/8/1116/8/12

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

フィンガープリント 「Joint learning of the embedding of words and entities for named entity disambiguation」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