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

Multilingual Knowledge Discovery in Digital Cultural Collections

Research Project

Project/Area Number 20K20135
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 90020:Library and information science, humanistic and social informatics-related
Research InstitutionRitsumeikan University

Principal Investigator

SONG Yuting  立命館大学, 情報理工学部, 助教 (50849388)

Project Period (FY) 2020-04-01 – 2022-03-31
Project Status Discontinued (Fiscal Year 2021)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2021: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
KeywordsEntity matching / MT Evaluation / Entity recognition / Relation extraction / Word embeddings / MT evaluation / Metadata translation / Knowledge extraction / Cultural collections / Multilingual information
Outline of Research at the Start

Recently, many cultural institutions have been making their cultural collections accessible through their metadata. However, multilingual knowledge in digital collections is less considered for accessing these collections.
This research aims to extract multilingual knowledge from metadata, including entities and object relations, by utilizing neural network based techniques of entity extraction and representation learning. The extracted knowledge can be applied to improve multilingual information access to digital cultural collections and help people understanding digital cultural objects.

Outline of Annual Research Achievements

This year we focused on improving the method of cross-lingual entity matching and collecting datasets for machine translation evaluation.
First, we proposed a novel method to identify records that refer to the same Japanese artwork entity in Japanese and English data sources. Our approach considered an entity as a sequence of attributes and employed a multilingual BERT-based network to enable cross-lingual entities to be compared without aligning the schema. In addition, we collected datasets and conducted further experiments to evaluate machine translations on translating ukiyo-e metadata records, especially the genre of bijin-e. In another work, we have investigated and evaluated the current state-of-the-art models to automatically discover entities and relations in short texts.

Report

(2 results)
  • 2021 Annual Research Report
  • 2020 Research-status Report
  • Research Products

    (6 results)

All 2021 2020

All Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results) Presentation (5 results) (of which Int'l Joint Research: 3 results)

  • [Journal Article] Learning Japanese-English Bilingual Word Embeddings by Using Language Specificity2021

    • Author(s)
      Yuting Song, Biligsaikhan Batjargal, and Akira Maeda
    • Journal Title

      International Journal of Asian Language Processing

      Volume: 30 Issue: 03 Pages: 1-18

    • DOI

      10.1142/s2717554520500149

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Joint Extraction of Clinical Entities and Relations Using Multi-head Selection Method2021

    • Author(s)
      FANG Xintao, SONG Yuting, MAEDA Akira
    • Organizer
      2021 International Conference on Asian Language Processing
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Linking Ukiyo-e Records across Languages: An Application of Cross-Language Record Linkage Techniques to Digital Cultural Collections2021

    • Author(s)
      Yuting Song, Biligsaikhan Batjargal, and Akira Maeda
    • Organizer
      The 5th Anniversary International Symposium of Asia-Japan Research at Ritsumeikan University
    • Related Report
      2020 Research-status Report
  • [Presentation] Joint Entity and Relation Extraction from Clinical Records Using Pre-trained Language Model2021

    • Author(s)
      FANG Xintao, SONG Yuting, Maeda Akira
    • Organizer
      第13回データ工学と情報マネジメントに関するフォーラム(DEIM2021)
    • Related Report
      2020 Research-status Report
  • [Presentation] A Preliminary Attempt to Evaluate Machine Translations of Ukiyo-e Metadata Records2020

    • Author(s)
      Yuting Song, Biligsaikhan Batjargal, and Akira Maeda
    • Organizer
      The 22nd International Conference on Asia-Pacific Digital Libraries
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Finding Identical Ukiyo-e Prints across Databases in Japanese, English and Dutch2020

    • Author(s)
      Yuting Song, Biligsaikhan Batjargal, and Akira Maeda
    • Organizer
      Digital Humanities 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2022-12-28  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi