Atsuki Yamaguchi

English | 日本語

Currently

I am a PhD student at the University of Sheffield, UK. My supervisors are Prof. Nikos Aletras and Prof. Aline Villavicencio. Previously, I was a full-time NLP researcher at Hitachi, Ltd. in Japan. Before that, I was a master’s student at the University of Sheffield, where I obtained an MSc. in Computer Science with Speech and Language Processing (with Distinction).

My curriculum vitae (CV) is available here (Updated on October 4th, 2023).

Research Interests

Natural Language Understanding, Natural Language Processing, Machine Learning

Recent Work

  • Explore simple pretraining alternatives for Transformer-based language representaion models
    The aim of this research is to investigate simple yet effective pretraining objectives.

    visualization of predicting issue weights in an end-to-end manner
    • Atsuki Yamaguchi, Hiroaki Ozaki, Terufumi Morishita, Gaku Morio and Yasuhiro Sogawa, “How does the task complexity of masked pretraining objectives affect downstream performance?,” Findings of the Association for Computational Linguistics: ACL 2023, July 2023. (Short paper)
    • Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina and Nikolaos Aletras, “Frustratingly Simple Pretraining Alternatives to Masked Language Modeling,” The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), Online, November 2021. (Short paper)
  • Support human-human negotiations using an end-to-end learning approach
    The aim of this research is to help negotiators form a better consensus.

    visualization of predicting issue weights in an end-to-end manner
    • Atsuki Yamaguchi, Kosui Iwasa and Katsuhide Fujita, “Dialogue Act-based Breakdown Detection in Negotiation Dialogues,” The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), Online, April 2021. (Acceptance rate: 23.3%; Long paper)
    • Atsuki Yamaguchi and Katsuhide Fujita, “Breakdown Detection in Negotiation Dialogues,” Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), New York, USA, Feburary 2020. (Student Abstract)
    • Atsuki Yamaguchi and Katsuhide Fujita, “Breakdown Detection in Negotiation Dialogues,” EurNLP 2019, London, United Kingdom, October 2019. (Acceptance rate: 30.5%; Non-archival)
    • Atsuki Yamaguchi, Kosui Iwasa and Katsuhide Fujita, “Predicting Issue Weights and Detecting Breakdowns in Negotiation Dialogue,” IEICE SIG-AI, Hokkaido, Japan, July 2019. (Regional conference)

Contact

You can send me messages via this contact form.

Updated on September 28, 2023