Improvement in Domain-Specific Named Entity Recognition by Utilizing the Real-World Data

• Tomori Suzushi

  Graduate School of Informatics, Kyoto University

• Ninomiya Takashi

  Graduate School of Science and Engineering, Ehime University

• Mori Shinsuke

  Academic Center for Computing and Media Studies, Kyoto University

Bibliographic Information

Other Title

• 実世界参照による分野特有の固有表現認識の精度向上
• ジツ セカイ サンショウ ニ ヨル ブンヤ トクユウ ノ コユウ ヒョウゲン ニンシキ ノ セイド コウジョウ

Abstract

In this paper, we propose a method that utilizes real-world data to improve named entity recognition (NER) for a particular domain. Our proposed method integrates a stacked auto-encoder (SAE) and a text-based deep neural network for achieving NER. Initially, we train the SAE using real-world data, then the entire deep neural network from sentences annotated with named entities (NEs) and accompanied by real world information. In our experiments, we chose Japanese chess as our subject. The dataset consists of pairs of a game state and commentary sentences about it annotated with game-specific NE tags. We conducted NER experiments and verified that referring to real-world data improves the NER accuracy.

Journal

• Journal of Natural Language Processing

  Journal of Natural Language Processing 24 (5), 655-668, 2017

  The Association for Natural Language Processing

Keywords

• Real World Information
• Neural Network
• Named Entity Recognition

Details

• CRID: 1390282679453115776
• NII Article ID: 130006507389
• NII Book ID: AN10472659
• DOI: 10.5715/jnlp.24.655
• ISSN: 21858314
• ISSN: 13407619
• NDL BIB ID: 028737108
• Web Site: http://id.ndl.go.jp/bib/028737108
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I028737108
• Web Site: https://www.jstage.jst.go.jp/article/jnlp/24/5/24_655/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed