Sho Yokoi (横井 祥)

alt text 

Sho Yokoi

Research Interest

  • Machine leanring for natural language processing, especially optimal transport and kernel methods

  • Increasing the resolution of metrics used in NLP

Publications (Refereed)

2021

  • Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, Makoto Yamada.
    Computationally Efficient Wasserstein Loss for Structured Labels.
    In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pp.1–7, 2021.
    [arXiv] [paper]

2020

2018

2017

2016

Publications (Domestic)

Non-refereed publications, Talks

Domestic Conferences, Workshops

Invited Talks

Education

  • Doctor of Information Science, April 2017 – March 2020.

    • Graduate School of Information Sciences, Tohoku University, Japan

    • Major: Natural Language Processing

    • Supervisor: Prof. Kentaro Inui

  • Master of Information Science, April 2015 – March 2017.

    • Graduate School of Information Sciences, Tohoku University, Japan

    • Major: Natural Language Processing

    • Supervisor: Prof. Kentaro Inui

  • Bachelor of Engineering, April 2011 – March 2015.

    • Undergraduate School of Informatics and Mathematical Science, Faculty of Engineering, Kyoto University, Japan

    • Major: Computer Science, Machine Learning

    • Supervisor: Prof. Hisashi Kashima

Work Experience

Research Assistant

Teaching

Teaching Assistant

  • Programming Practice A (C language), Tohoku University, Spring 2017.

  • Information Communication Theory (Python), Tohoku University, Autumn 2016.

  • Web Computing (Python), Tohoku University, Spring 2016.

  • Programming Practice A (C language), Tohoku University, Spring 2016.

  • Basic Seminar for Competitive Programming and AI Programming (C language, C++), Tohoku University, Spring 2015.

  • Programming Practice A (C language), Tohoku University, Spring 2015.

Professional Activities

Research Grant

Program Committee

Member