Improvement in Domain Specific Word Segmentation by Symbol Grounding

• Tomori Suzushi

  Graduate School of Informatics, Kyoto University

• Kameko Hirotaka

  Graduate School of Engineering, The University of Tokyo

• Ninomiya Takashi

  Graduate School of Science and Engineering, Ehime University

• Mori Shinsuke

  Academic Center for Computing and Media Studies, Kyoto University

• Tsuruoka Yoshimasa

  Graduate School of Engineering, The University of Tokyo

Bibliographic Information

Other Title

• シンボルグラウンディングによる分野特有の単語分割の精度向上
• シンボルグラウンディング ニ ヨル ブンヤ トクユウ ノ タンゴ ブンカツ ノ セイド コウジョウ

Abstract

We propose a novel framework for improving a word segmenter using information acquired from symbol grounding. The framework uses a dataset consisting of pairs of non-textual information and a commentary. We generate a pseudo-stochastically segmented corpus from the commentaries, and then build a neural network to predict relationships between non-textual information and the words. We generate a domain specific term dictionary by using the neural network for word segmenter. We applied our method to game records of Japanese chess with commentaries. The experimental results show that the accuracy of a word segmenter can be improved by incorporating the generated dictionary.

Journal

• Journal of Natural Language Processing

  Journal of Natural Language Processing 24 (3), 447-461, 2017

  The Association for Natural Language Processing

Keywords

• Symbol Grounding
• Word Segmentation
• Dictionary

Details

• CRID: 1390001204474461824
• NII Article ID: 130006078455
• NII Book ID: AN10472659
• DOI: 10.5715/jnlp.24.447
• ISSN: 21858314
• ISSN: 13407619
• NDL BIB ID: 028334316
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I028334316
• Web Site: https://www.jstage.jst.go.jp/article/jnlp/24/3/24_447/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed