Semi-Supervised Extractive Question Summarizer Using Question-Answer Pairs and its Learning Methods

DOI Web Site Web Site 30 References
  • ISHIGAKI Tatsuya
    Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST)
  • Machida Kazuya
    Department of Information and Communications Engineering, School of Engineering, Tokyo Institute of Technology
  • Kobayashi Hayato
    Yahoo Japan Corporation
  • TAKAMURA Hiroya
    Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST) Laboratory for Future Interdisciplinary Research of Science and Technology (FIRST), Institute of Innovative Research (IIR), Tokyo Institute of Technology
  • OKUMURA Manabu
    Laboratory for Future Interdisciplinary Research of Science and Technology (FIRST), Institute of Innovative Research (IIR), Tokyo Institute of Technology

Bibliographic Information

Other Title
  • 質問－回答ペアを活用する 半教師あり抽出型質問要約モデルとその学習法
  • シツモン-カイトウ ペア オ カツヨウ スル ハンキョウシ アリ チュウシュツガタ シツモン ヨウヤク モデル ト ソノ ガクシュウホウ

Search this article

Description

<p>We treat extractive summarization for questions. Neural extractive summarizers often require much labeled training data. Obtaining such labels is difficult, especially for user-generated content, such as questions posted on community question answering services. In this paper, we propose semi-supervised extractive summarizers for such questions that exploit question-answer pairs to alleviate the problem of insufficient labeled data. To this end, we propose several learning methods, namely pretraining, multi-task learning, distant supervision, and sampling methods, to examine how to effectively use such unlabeled paired data. Experimental results show that multi-task training performs well with an appropriate sampling method or distant supervision, especially when the labeled data is small.</p>

Journal

References(30)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top