A Linguistics-Driven Approach to Statistical Parsing for Low-Resourced Languages

• BOONKWAN Prachya

  Language and Semantic Technology Laboratory, National Electronics and Computer Technology Center

• SUPNITHI Thepchai

  Language and Semantic Technology Laboratory, National Electronics and Computer Technology Center

抄録

Developing a practical and accurate statistical parser for low-resourced languages is a hard problem, because it requires large-scale treebanks, which are expensive and labor-intensive to build from scratch. Unsupervised grammar induction theoretically offers a way to overcome this hurdle by learning hidden syntactic structures from raw text automatically. The accuracy of grammar induction is still impractically low because frequent collocations of non-linguistically associable units are commonly found, resulting in dependency attachment errors. We introduce a novel approach to building a statistical parser for low-resourced languages by using language parameters as a guide for grammar induction. The intuition of this paper is: most dependency attachment errors are frequently used word orders which can be captured by a small prescribed set of linguistic constraints, while the rest of the language can be learned statistically by grammar induction. We then show that covering the most frequent grammar rules via our language parameters has a strong impact on the parsing accuracy in 12 languages.

収録刊行物

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E98.D (5), 1045-1052, 2015

  一般社団法人 電子情報通信学会

キーワード

• statistical parsing
• grammar induction
• language parameters
• Universal Grammar
• treebank

詳細情報

• CRID: 1390001204377424896
• NII論文ID: 130005067748
• DOI: 10.1587/transinf.2014dap0024
• ISSN: 17451361
• ISSN: 09168532
• Web Site: https://www.jstage.jst.go.jp/article/transinf/E98.D/5/E98.D_2014DAP0024/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可