Shohei Higashiyama

Research Interests

  • Natural Language Processing

Work Experience

  • National Institute of Information and Communications Technology (NICT)

    • April 2022 to present: Researcher

    • July 2019 to March 2022: Technical Researcher

    • May 2017 to April 2019: Researcher (Transferred employee)

  • NEC Corporation

    • April 2014 to June 2019: Researcher

Education

  • Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST)

    • March 2022: Doctor of Engineering

  • Graduate School of System Informatics, Kobe University

    • March 2014: M.S. in System Informatics

  • Faculty of Engineering, Kobe University

    • March 2012: B.S. in Engineering

Selected Publications

  1. Shohei Higashiyama, Masao Utiyama, Taro Watanabe, and Eiichiro Sumita, A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization, In Proceedings of the 7th Workshop on Noisy User-generated Text (W-NUT), pp. 67-80, Online, November, 2021. [paper] Best Paper Award

  2. Shohei Higashiyama, Masao Utiyama, Taro Watanabe, and Eiichiro Sumita, User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization, In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 5532-5541, Online, June 2021. [paper] [arXiv] [dataset]

  3. Shohei Higashiyama, Masao Utiyama, Yuji Matsumoto, Taro Watanabe, and Eiichiro Sumita, Auxiliary Lexicon Word Prediction for Cross-Domain Word Segmentation, Journal of Natural Language Processing, Vol. 27, No. 3, pp. 573-598, September 2020. [paper]

  4. Shohei Higashiyama, Masao Utiyama, Eiichiro Sumita, Masao Ideuchi, Yoshiaki Oida, Yohei Sakamoto, Isaac Okada, and Yuji Matsumoto, Character-to-Word Attention for Word Segmentation, Journal of Natural Language Processing, Vol. 27, No. 3, pp. 499-530, September 2020. [paper] Best Paper Award

  5. Shohei Higashiyama, Masao Utiyama, Eiichiro Sumita, Masao Ideuchi, Yoshiaki Oida, Yohei Sakamoto, and Isaac Okada, Incorporating Word Attention into Character-Based Word Segmentation, In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 2699-2709, Minneapolis, USA, June 2019. [paper] [code]

Language Resources & Software

  • JLexNorm: Corpora for Japanese Morphological Analysis and Lexical Normalization

  • SeikaNLP: An NLP toolkit, including a neural word segmenter using word attention

Awards

  1. Best Paper Award at the 7th Workshop on Noisy User-generated Text (W-NUT), "A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization", November, 2021.

  2. Best Paper Award of the Association for Natural Language Processing, "Character-to-Word Attention for Word Segmentation", March 2021.

  3. Best Paper Award at the International Conference on Computer and Information Sciences (ICCOINS 2014), "A Cost-Sensitive Approach to Named Entity Recognition with Category Hierarchy", June 2014.

  4. Student Encouragement Award at the 74th National Convention of IPSJ, "カテゴリ階層を考慮した固有表現抽出", March 2012.

Academic Activities