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

Establishment of causal instance recognition techniques for economic scenario analysis

Research Project

Project/Area Number 21K12010
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 InstitutionHokkaido University (2023)
The University of Tokyo (2021-2022)

Principal Investigator

Sakaji Hiroki  北海道大学, 情報科学研究院, 准教授 (70722809)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2023: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2022: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2021: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords因果関係 / 因果関係インスタンス / 事前学習モデル / グラフニューラルネットワーク / テキストマイニング / 因果関係インスタンス認識 / 社会イベント分析
Outline of Research at the Start

本研究の目的は、日本語・英語問わず、様々な金融テキストデータから、因果関係インスタンスを認識することで、社会イベント発生から個々の影響へのパスを明らかにすることである。これを達成するために、個々の因果関係インスタンスを認識する技術、抽出した因果関係インスタンスを用いて正確に因果チェーンを構築する技術の開発を行う。加えて、構築した因果チェーンを用いて国、地域、企業と異なる立場に基づくシナリオ分析可能なフレームワークを構築する。

Outline of Final Research Achievements

I conducted causal instance extraction experiments using tagged earnings release data, tagged English Reuters news articles, and FinCausal datasets to develop a method that can extract causal instances from Japanese and English documents. As a result, I succeeded in developing a method that can extract causal instances with higher accuracy than existing methods by combining BERT and graph neural networks.
Finally, this research was accepted for publication in a peer-reviewed journal under the title “FinancialCausality Extraction based on Universal Dependencies and Clue Expressions.

Academic Significance and Societal Importance of the Research Achievements

因果関係インスタンス抽出手法を作成するために、BERTモデルの改良の検討も行った。その結果、金融特化のBERTモデルの構築ができ、こちらをhugging faceにて公開した。また、その過程で得られた他のBERTモデルも公開し、公開したBERTモデルは幅広く利用されている。
作成した因果関係インスタンス抽出手法は、日本語と英語のみならず、学習データさえ存在すれば、他の言語でも利用可能であることから、今後の研究発展が期待される。

Report

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

    (19 results)

All 2023 2022 2021 Other

All Journal Article (2 results) (of which Peer Reviewed: 2 results,  Open Access: 1 results) Presentation (11 results) (of which Int'l Joint Research: 5 results) Remarks (6 results)

  • [Journal Article] Financial Causality Extraction Based on Universal Dependencies and Clue Expressions2023

    • Author(s)
      Sakaji Hiroki、Izumi Kiyoshi
    • Journal Title

      New Generation Computing

      Volume: 41 Issue: 4 Pages: 839-857

    • DOI

      10.1007/s00354-023-00233-2

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Constructing and analyzing domain-specific language model for financial text mining2023

    • Author(s)
      Masahiro Suzuki, Hiroki Sakaji, Masanori Hirano, Kiyoshi Izumi
    • Journal Title

      Information Processing & Management

      Volume: 60 Issue: 2 Pages: 103194-103194

    • DOI

      10.1016/j.ipm.2022.103194

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Presentation] Indexing and Visualization of Climate Change Narratives Using BERT and Causal Extraction2023

    • Author(s)
      Hiroki Sakaji, Noriyasu Kaneda
    • Organizer
      2023 IEEE International Conference on Big Data
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models2023

    • Author(s)
      Masahiro Suzuki, Masanori Hirano, Hiroki Sakaji
    • Organizer
      2023 IEEE International Conference on Big Data
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] llm-japanese-dataset v0: Construction of Japanese Chat Dataset for Large Language Models and its Methodology2023

    • Author(s)
      Masanori Hirano, Masahiro Suzuki, Hiroki Sakaji
    • Organizer
      The 12th International Workshop on Web Services and Social Media (WSSM-2023) in The 26th International Conference on Network-Based Information Systems (NBiS-2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Summarization of Investment Reports Using Pre-trained Model2023

    • Author(s)
      Hiroki Sakaji, Ryotaro Kobayashi, Kiyoshi Izumi, Hiroyuki Mitsugi, Wataru Kuramoto
    • Organizer
      13th International Conference on Smart Computing and Artificial Intelligence (SCAI 2023) in 14th IIAI International Congress on Advanced Applied Informatics (IIAI AAI 2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 銘柄特徴と投資家特性を考慮した株式銘柄推薦の個別化2023

    • Author(s)
      高柳剛弘, 坂地泰紀, 和泉潔
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Related Report
      2022 Research-status Report
  • [Presentation] BERTとGATを用いた金融テキストにおける因果関係を含む文の判定2023

    • Author(s)
      小林涼太郎, 坂地泰紀, 和泉潔
    • Organizer
      言語処理学会第29回年次大会(NLP2023)
    • Related Report
      2022 Research-status Report
  • [Presentation] Gradual Further Pre-training Architecture for Economics/Finance Domain Adaptation of Language Model2022

    • Author(s)
      Hiroki Sakaji, Masahiro Suzuki, Kiyoshi Izumi, Hiroyuki Mitsugi
    • Organizer
      2022 IEEE International Conference on Big Data (IEEE BigData 2022)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] 個別銘柄情報と銘柄間情報を利用したテーマ株抽出手法の提案2022

    • Author(s)
      高柳剛弘, 坂地泰紀, 和泉潔
    • Organizer
      2022年度人工知能学会全国大会
    • Related Report
      2022 Research-status Report
  • [Presentation] 系列ラベリングによる原因・結果表現抽出の試み2021

    • Author(s)
      坂地泰紀, 和泉潔, 加藤惇雄, 長尾慎太郎
    • Organizer
      第18回テキストアナリティクス・シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] 鈴木雅弘, 坂地泰紀, 平野正徳, 和泉潔2021

    • Author(s)
      金融ドメインにおける事前学習BERTモデルの性能検証
    • Organizer
      第18回テキストアナリティクス・シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] 金融文書を用いた事前学習言語モデルの構築と検証2021

    • Author(s)
      鈴木雅弘, 坂地泰紀, 平野正徳, 和泉潔
    • Organizer
      人工知能学会第27回金融情報学研究会
    • Related Report
      2021 Research-status Report
  • [Remarks] Hiroki's page

    • URL

      https://tetsuwaka.net/

    • Related Report
      2023 Annual Research Report
  • [Remarks] 事前学習言語モデル

    • URL

      https://huggingface.co/izumi-lab

    • Related Report
      2023 Annual Research Report
  • [Remarks] 日本語大規模言語モデル (by SHS)

    • URL

      https://llm.msuzuki.me/

    • Related Report
      2023 Annual Research Report
  • [Remarks] Hiroki's page

    • URL

      https://testuwaka.net/

    • Related Report
      2022 Research-status Report
  • [Remarks] 事前学習言語モデル

    • URL

      https://sites.google.com/socsim.org/izumi-lab/tools/language-model

    • Related Report
      2022 Research-status Report
  • [Remarks] Hiroki's page

    • URL

      http://tetsuwaka.net/

    • Related Report
      2021 Research-status Report

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi