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

Building Semantic Frames using Contextualized Word Embeddings

Research Project

Project/Area Number 21K12012
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionNagoya University

Principal Investigator

Sasano Ryohei  名古屋大学, 情報学研究科, 准教授 (70603918)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2023: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2022: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2021: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords意味フレーム / 文脈化単語埋め込み
Outline of Research at the Start

本研究では、文脈を考慮した単語ベクトル表現(文脈化単語埋め込み)が、人が常識として持つ経験的知識をどの程度捉えているかを明らかにすることを目的とし、日本語と英語を対象に、文脈化単語埋め込みを用いた、大規模コーパスからの意味フレームの自動構築に取り組む。さらに、自動構築したフレーム知識を、人手で整備された知識フレームと対応付けることで、人にとって理解しやすく、かつ、単語埋め込み技術と親和性の高いフレーム知識の構築を目指す。

Outline of Final Research Achievements

In this research project, we worked mainly on automatically constructing semantic frame knowledge using contextualized word embeddings. Specifically, we proposed a method that uses masked word embedding and two-stage clustering for the frame induction task, in which verbs are clustered according to the frames they evoke, and a method that performs fine-tuning of the contextualized word embedding model based on deep metric learning followed by clustering of the verbs. The proposed method achieves a higher performance than the existing methods. In frame element knowledge acquisition task, we proposed a method that performs fine-tuning of the contextualized word embedding model based on deep metric learning followed by clustering of agruments of frame evoking words, and achieved a higher performance than the existing methods.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果は、これまで人手で行われてきた意味フレーム資源の開発コストの低減する可能性がある。具体的には、これまで大規模な意味フレーム資源が整備されてこなかった言語を対象に意味フレームを自動構築したり、人手によるフレーム資源の整備の補助に用いることが可能である。また、大規模なコーパスから学習された大規模言語モデルが、人が言語理解の前提として持つ経験的知識をどの程度含んでいるかの分析に貢献する可能性がある。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (9 results)

All 2024 2023 2022 2021

All Journal Article (3 results) (of which Peer Reviewed: 3 results,  Open Access: 3 results) Presentation (6 results) (of which Int'l Joint Research: 6 results)

  • [Journal Article] 深層距離学習を用いた意味フレーム構築におけるフレーム要素知識の自動獲得2024

    • Author(s)
      山田康輔, 笹野遼平, 武田浩一
    • Journal Title

      情報処理学会論文誌

      Volume: 65

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Semantic Frame Induction with Deep Metric Learning2023

    • Author(s)
      山田康輔, 笹野遼平, 武田浩一
    • Journal Title

      Journal of Natural Language Processing

      Volume: 30 Issue: 4 Pages: 1130-1150

    • DOI

      10.5715/jnlp.30.1130

    • ISSN
      1340-7619, 2185-8314
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] マスクされた単語埋め込みと2段階クラスタリングを用いた動詞の意味フレーム推定2022

    • Author(s)
      山田康輔, 笹野遼平, 武田浩一
    • Journal Title

      自然言語処理

      Volume: 29

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Argument Clustering with Deep Metric Learning for Semantic Frame Induction2023

    • Author(s)
      Kosuke Yamada, Ryohei Sasano, Koichi Takeda
    • Organizer
      Findings of the Association for Computational Linguistics: ACL 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Transformer-based Live Update Generation for Soccer Matches from Microblog Posts2023

    • Author(s)
      Masashi Oshika, Kosuke Yamada, Ryohei Sasano, Koichi Takeda
    • Organizer
      The 2023 Conference on Empirical Methods in Natural Language Processing
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Semantic Frame Induction with Deep Metric Learning2023

    • Author(s)
      Kosuke Yamada, Ryohei Sasano, Koichi Takeda
    • Organizer
      the 17th Conference of the European Chapter of the Association for Computational Linguistics
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] Cross-lingual Linking of Automatically Constructed Frames and FrameNet2022

    • Author(s)
      Ryohei Sasano
    • Organizer
      The 13th International Conference on Language Resources and Evaluation
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering2021

    • Author(s)
      Kosuke Yamada, Ryohei Sasano, Koichi Takeda
    • Organizer
      The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Verb Sense Clustering Using Contextualized Word Representations for Semantic Frame Induction2021

    • Author(s)
      Kosuke Yamada, Ryohei Sasano, Koichi Takeda
    • Organizer
      Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi