Machine-Learning-Based Transformation of Japanese Passive Sentences into Active by Separating Training Data into Each Input Particle

• MURATA Masaki

  Knowledge Creating Communication Research Center, National Institute of Information and Communications Technology

• KANAMARU Toshiyuki

  Knowledge Creating Communication Research Center, National Institute of Information and Communications Technology

• SHIRADO Tamotsu

  Knowledge Creating Communication Research Center, National Institute of Information and Communications Technology

• ISAHARA Hitoshi

  Knowledge Creating Communication Research Center, National Institute of Information and Communications Technology

Bibliographic Information

Other Title

• 入力文の格助詞ごとに学習データを分割した機械学習による受身文の能動文への変換における格助詞の変換
• ニュウリョクブン ノ カクジョシ ゴト ニ ガクシュウ データ オ ブンカツシタ キカイ ガクシュウ ニ ヨル ウケミブン ノ ノウドウブン エノ ヘンカン ニ オケル カクジョシ ノ ヘンカン

Abstract

We developed a new method of transforming Japanese case particles when transforming Japanese passive sentences into active sentences. This method separates training data into each input particle and uses machine learning for each particle. We also used numerous rich features for learning. Murata et al. conducted a previous study on transforming Japanese passive sentences into active sentences [2]. They used machine learning but did not separate training data for any input particles and did not have many rich features for learning. They achieved an accuracy rate of 89.77%. We added many rich features to those used in Murata et al.'s study and obtained an accuracy rate of 92.00%. In addition, we used our method of separating training data into each input particle and using machine learning for each particle, and obtained an accuracy rate of 94.30%. We confirmed the significance of these improvements through a statistical test. We also conducted experiments utilizing traditional methods using verb dictionaries and manually prepared heuristic rules and confirmed that our method achieved much higher accuracy rates than traditional methods.

Journal

• Transactions of the Institute of Systems, Control and Information Engineers

  Transactions of the Institute of Systems, Control and Information Engineers 21 (6), 165-175, 2008

  THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)

Keywords

• machine learning
• transformation
• passive
• active
• separating training data

Details

• CRID: 1390282680142998528
• NII Article ID: 10021064553
• NII Book ID: AN1013280X
• DOI: 10.5687/iscie.21.165
• ISSN: 2185811X
• ISSN: 13425668
• NDL BIB ID: 9526248
• Web Site: http://id.ndl.go.jp/bib/9526248
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I9526248
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed