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

Unified word embeddings for domain Ontologies and large-scale documents

Research Project

Project/Area Number 17K00318
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Intelligent informatics
Research InstitutionToyota Technological Institute

Principal Investigator

Yutaka Sasaki  豊田工業大学, 工学(系)研究科(研究院), 教授 (60395019)

Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
KeywordsPoincare埋め込み / Poincare Glove / レトロフィッティング / オントロジー埋め込み / 交通知識ベース / Poincare GloVe / 記号・ニューラル学習 / 埋め込みベクトル / オントロジ / グラフ埋め込み / WSD / Word Embedding / Onology
Outline of Final Research Achievements

For applying deep neural learning, it is crucial to represent words and sentences as numerical vectors that reflect the original semantic contents. In this study, we developed a new method to integrate documents information and knowledge structures into a single space on the basis of the Poincare embedding technology. Our retrofitting method maps textual Poincare GloVe embedding vectors to the hypernym Poincare embedding space so that the similarity among textual embedding vectors are preserved. Experimental results show that we can improve hypernym detection performances of the textural Poincare embedding vectors by retrofitting the textual vectors to the skeleton of hypernym embedding vectors. In addition, we created a traffic-rule corpus that has links from traffic terms to a traffic Ontology concepts and relations.

Academic Significance and Societal Importance of the Research Achievements

単語や文を数値ベクトルとして表現する技術は深層学習において非常に重要である.しかし,これまで単語を数値ベクトルとして表現する技術と知識構造を埋め込みベクトルとして表現する技術はそれぞれ独立に研究されてきた.特に,Poincare埋め込みは単語の上位下位関係の表現に適しており,知識ベースのベクトル表現に非常に適した方法であるが,扱える単語に制約があった.本研究では,レトロフィッティング法により,大量文書から作成したPoincareベクトルを概念構造から作成したPorincare埋め込みに適合させた点に意義がある.また,交通に関する知識と文書をリンクした新コーパスを一般公開し社会に貢献する.

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (7 results)

All 2020 2018 2017 Other

All Int'l Joint Research (1 results) Presentation (6 results) (of which Int'l Joint Research: 3 results)

  • [Int'l Joint Research] TTIC(米国)

    • Related Report
      2017 Research-status Report
  • [Presentation] Poincae GloVe ベクトルのレトロフィッティング2020

    • Author(s)
      村瀬敦也, 三輪誠, 佐々木裕
    • Organizer
      言語処理学会第26回年次大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] オントロジー形式による交通関係アノテーション2020

    • Author(s)
      Savong Bou, 鈴木直樹, 三輪誠, 佐々木裕
    • Organizer
      言語処理学会第26回年次大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] オントロジー形式アノテーションを対象とした交通用語・関係抽出と正誤問題の回答2020

    • Author(s)
      鈴木直樹, Savong Bou, 三輪誠, 佐々木裕
    • Organizer
      言語処理学会第26回年次大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Ontology-Style Relation Annotation: A Case Study2020

    • Author(s)
      Savong Bou, Naoki Suzuki, Makoto Miwa, Yutaka Sasaki
    • Organizer
      12th Edition of its Language Resources and Evaluation Conference (accepted)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Semantic Graph Embeddings and a Neural Language Model for Word Sense Disambiguation2018

    • Author(s)
      Marc Evrard, Makoto Miwa, Yutaka Sasaki
    • Organizer
      Second International Workshop on Symbolic-Neural Learning (SNL2018)
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] TTI's Approaches to Symbolic-Neural Learning2017

    • Author(s)
      Marc Evrard, Makoto Miwa, Yutaka Sasaki
    • Organizer
      International Workshop on Symbokic-Neural Learning
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2017-04-28   Modified: 2022-06-07  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi