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

Takase Sho  高瀬 翔

ORCIDConnect your ORCID iD *help
Researcher Number 40817483
Other IDs
Affiliation (based on the past Project Information) *help 2020 – 2022: 東京工業大学, 情報理工学院, 助教
2018 – 2020: 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, 協創情報研究部, リサーチアソシエイト
2018 – 2019: 東京工業大学, 情報理工学院, 研究員
Review Section/Research Field
Principal Investigator
Basic Section 61030:Intelligent informatics-related
Except Principal Investigator
Basic Section 61030:Intelligent informatics-related
Keywords
Principal Investigator
機械翻訳 / ニューラルネットワーク / 自然言語処理 / 言語モデル
Except Principal Investigator
高速フーリエ変換 / テンソル分解 / 知識グラフ / ニューラルネットワーク / 行列分解
  • Research Projects

    (3 results)
  • Research Products

    (11 results)
  • Co-Researchers

    (2 People)
  •  自然言語処理における敵対的な摂動の高速な計算Principal Investigator

    • Principal Investigator
      高瀬 翔
    • Project Period (FY)
      2021 – 2022
    • Research Category
      Grant-in-Aid for Early-Career Scientists
    • Review Section
      Basic Section 61030:Intelligent informatics-related
    • Research Institution
      Tokyo Institute of Technology
  •  Matrix Factorization-based Efficient Learning for Neural Networks

    • Principal Investigator
      Hayashi Katsuhiko
    • Project Period (FY)
      2018 – 2020
    • Research Category
      Grant-in-Aid for Scientific Research (C)
    • Review Section
      Basic Section 61030:Intelligent informatics-related
    • Research Institution
      Gunma University
      The University of Tokyo
      Osaka University
  •  Efficient training for neural encoder-decoders on a large amount of training dataPrincipal Investigator

    • Principal Investigator
      Takase Sho
    • Project Period (FY)
      2018 – 2020
    • Research Category
      Grant-in-Aid for Early-Career Scientists
    • Review Section
      Basic Section 61030:Intelligent informatics-related
    • Research Institution
      Tokyo Institute of Technology

All 2022 2021 2020 2019 2018

All Journal Article Presentation

  • [Journal Article] Multi-Task Learning for Cross-Lingual Abstractive Summarization2022

    • Author(s)
      Sho Takase, Naoaki Okazaki
    • Journal Title

      Proceedings of the Thirteenth Language Resources and Evaluation Conference

      Volume: LREC 2022 Pages: 3008-3016

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-21K17800
  • [Journal Article] Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation2022

    • Author(s)
      Sho Takase, Tatsuya Hiraoka, Naoaki Okazaki
    • Journal Title

      Findings of the Association for Computational Linguistics: ACL 2022

      Volume: Findings of ACL 2022 Pages: 2536-2541

    • DOI

      10.18653/v1/2022.findings-acl.199

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-21K17800
  • [Journal Article] Rethinking Perturbations in Encoder-Decoders for Fast Training2021

    • Author(s)
      Sho Takase, Shun Kiyono
    • Journal Title

      Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

      Volume: NAACL 2021 Pages: 5767-5780

    • DOI

      10.18653/v1/2021.naacl-main.460

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-21K17800
  • [Presentation] Transformerを多層にする際の勾配消失問題と解決法について2022

    • Author(s)
      高瀬翔
    • Organizer
      言語処理学会
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K17800
  • [Presentation] Multi-Task Learning for Cross-Lingual Abstractive Summarization2022

    • Author(s)
      高瀬翔
    • Organizer
      LREC 2022
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K17800
  • [Presentation] Rethinking Perturbations in Encoder-Decoders for Fast Training2021

    • Author(s)
      Sho Takase
    • Organizer
      NAACL
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-21K17800
  • [Presentation] All Word Embeddings from One Embedding2020

    • Author(s)
      Sho Takase, Sosuke Kobayashi
    • Organizer
      Neural Information Processing Systems
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K18119
  • [Presentation] Character n-gram Embeddings to Improve RNN Language Models2019

    • Author(s)
      Sho Takase, Jun Suzuki, Masaaki Nagata
    • Organizer
      Thirty-Third AAAI Conference on Artificial Intelligence
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K18119
  • [Presentation] Positional Encoding to Control Output Sequence Length2019

    • Author(s)
      Sho Takase, Naoaki Okazaki
    • Organizer
      North American Chapter of the Association for Computational Linguistics
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K18119
  • [Presentation] 位置エンコーディングを用いた出力長制御2019

    • Author(s)
      高瀬翔, 岡崎直観
    • Organizer
      言語処理学会年次大会
    • Data Source
      KAKENHI-PROJECT-18K18119
  • [Presentation] Direct Output Connection for a High-Rank Language Model2018

    • Author(s)
      Sho Takase, Jun Suzuki, Masaaki Nagata
    • Organizer
      Empirical Methods in Natural Language Processing
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-18K18119
  • 1.  Hayashi Katsuhiko (50725794)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 2.  上垣外 英剛 (40817649)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results

URL: 

Are you sure that you want to link your ORCID iD to your KAKEN Researcher profile?
* This action can be performed only by the researcher himself/herself who is listed on the KAKEN Researcher’s page. Are you sure that this KAKEN Researcher’s page is your page?

この研究者とORCID iDの連携を行いますか?
※ この処理は、研究者本人だけが実行できます。

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi