• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Efficient and accurate natural language analysis with lookahead of analysis actions

Research Project

Project/Area Number 23700162
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Intelligent informatics
Research InstitutionThe University of Tokyo

Principal Investigator

TSURUOKA Yoshimasa  東京大学, 大学院・工学系研究科, 准教授 (50566362)

Project Period (FY) 2011 – 2012
Project Status Completed (Fiscal Year 2012)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2012: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2011: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Keywords自然言語処理 / 機械学習 / 品詞タグ付け / 固有表現認識 / 構文解析 / 探索 / アルゴリズム / 評価関数 / チャンキング / 係り受け解析
Research Abstract

We have developed a novel machine learning algorithm that can be used for various natural language processing tasks such as part-of-speech tagging and parsing. The algorithm enables us to incorporate a look-ahead mechanism into a history-based model and significantly improve its accuracy. Experimental results demonstrate that our approach outperforms conditional random field models, which are currently the standard approach in the field, in several natural language processing tasks.

Report

(3 results)
  • 2012 Annual Research Report   Final Research Report ( PDF )
  • 2011 Research-status Report
  • Research Products

    (6 results)

All 2013 2011 Other

All Presentation (4 results) Remarks (2 results)

  • [Presentation] 先読みを用いた単語系列ラベリングへの最易優先方策の適用2013

    • Author(s)
      佐野峻平,三輪誠,鶴岡慶雅,近山隆
    • Organizer
      言語処理学会第19回年次大会
    • Related Report
      2012 Final Research Report
  • [Presentation] 先読みを用いた単語系列ラベリングへの最易優先方策の適用2013

    • Author(s)
      佐野峻平
    • Organizer
      言語処理学会第19回年次大会
    • Place of Presentation
      名古屋・名古屋大学
    • Related Report
      2012 Annual Research Report
  • [Presentation] Learning with Lookahead: Can History-Based Models Rival Globally Optimized Models?2011

    • Author(s)
      Yoshimasa Tsuruoka, Yusuke Miyao and Jun'ichi Kazama
    • Organizer
      Fifteenth Conference on Computational Natural Language Learning
    • Place of Presentation
      Portland, Oregan, USA
    • Related Report
      2011 Research-status Report
  • [Presentation] Can History-Based Models Rival Globally Optimized Models?

    • Author(s)
      Yoshimasa Tsuruoka, Yusuke Miyao, and Jun'ichi Kazama. 2011. Learning with Lookahead
    • Organizer
      In Proceedings of the Fifteenth Conference on Computational Natural Language Learning (CoNLL)
    • Related Report
      2012 Final Research Report
  • [Remarks]

    • URL

      http://www.logos.ic.i.u-tokyo.ac.jp/~tsuruoka/conll11la/

    • Related Report
      2012 Final Research Report
  • [Remarks]

    • URL

      http://www.logos.ic.i.u-tokyo.ac.jp/~tsuruoka/conll11la/

    • Related Report
      2011 Research-status Report

URL: 

Published: 2011-08-05   Modified: 2019-07-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi