Kentaro Inui - MBZUAI MBZUAI

Kentaro Inui

Professor of Natural Language Processing

Research Interests

Professor Inui’s ongoing research centers on the inner workings and interpretability of language and multi-modal models, for example, how they internally represent and organize knowledge about the world and how mechanistic explanations of model behavior can be developed, seeking to enhance the explainability, transparency, and trustworthiness of NLP systems. He also investigates how interpretability links to fields like cognitive science, neuroscience, and robotics. Additionally, he is interested in applying NLP to education, including explainable writing assessment and argumentation analysis for learning support.

Email

Before joining MBZUAI, Professor Inui led the Natural Language Processing Lab at Tohoku University for over a decade and directed the Natural Language Understanding Team at the RIKEN Center for the Advanced Intelligence Project, where he maintains active collaborations.

He began his career as an Assistant Professor at the Tokyo Institute of Technology in 1995, later becoming an Associate Professor at the Kyushu Institute of Technology and the Nara Institute of Science and Technology before joining Tohoku University in 2010. He also worked as a visiting researcher at the University of Sussex in 2004.

Over his career, he has served as the editor-in-chief of the Journal of Information Processing and the Journal of Natural Language Processing, and as Chairperson of the Association for Natural Language Processing in Japan. He also took on the role of General Chair for EMNLP-IJCNLP 2019 and, more recently, serves as General Chair for IJCNLP-AACL 2025 and Program Co-chair for EACL 2026.

  • Ph.D. in computer science from the Tokyo Institute of Technology, Japan.
  • Master of Engineering in computer science from the Tokyo Institute of Technology, Japan.
  • Commendation for Science and Technology by the Minister of MEXT, Japan, 2022
  • Google Focused Research Award, 2019
  • Best Paper Award, Journal of Natural Language Processing, 2021
  • Best Paper Award, Transactions of the Japanese Society for Artificial Intelligence, 2017
  • Outstanding Paper Award, EACL 2017
  • IBM Faculty Award, 2016
  • Docomo Mobile Science Award, 2015
  • Best Paper Award (Computation), PACLIC 2015
  • Best Paper Award, AMT 2014
  • 20th Anniversary Best Paper Award, Journal of Natural Language Processing, 2014
  • Best Paper Award (First Place), Journal of Natural Language Processing, 2014
  • Best Paper Award (First Place), Annual Meeting of the Association for Natural Language Processing, Japan, 2020, 2016, 2015, 2014
  • Best Paper Award, Annual Meeting of the Association for Natural Language Processing, Japan, 2022, 2021, 2020, 2019, 2018, 2017, 2016
  • Chairperson of the Japanese Association for Natural Language Processing, 2022-
  • General Chair of EMNLP-IJCNLP, 2019
  • Executive Committee Member of the Asian Federation of Natural Language Processing, 2019–2021
  • Associate Member of the Science Council of Japan, 2018–
  • Editor in Chief of the Journal of Natural Language Processing, 2018-2019
  • Director of the NPO FactCheck Initiative Japan, 2017–
  • Editor in Chief of the Journal of Information Processing, 2014-2015
  • Editorial Board Member of Computational Linguistics, 2009-2011

  • Hiroaki Funayama, Yuya Asazuma, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki and Kentaro Inui. Reducing the Cost: Cross-Prompt Pre-Finetuning for Short Answer Scoring. The 24th International Conference on Artificial Intelligence in Education (AIED 2023), pp.78–89, 2023.
  • Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Ana Brassard, Masashi Yoshikawa, Keisuke Sakaguchi and Kentaro Inui. Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning? In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), pp.1343-1354, 2023.
  • Yuko Tanaka, Miwa Inuzuka, Hiromi Arai, Yoichi Takahashi, Minao Kukita and Kentaro Inui. Who Does Not Benefit from Fact-Checking Websites? A Psychological Characteristic Predicts the Selective Avoidance of Clicking Uncongenial Facts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI 2023), pp.1–17, 2023.
  • Qin Dai, Benjamin Heinzerling, Kentaro Inui. Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), 15 pages, 2022.
  • Tatsuki Kuribayashi, Yohei Oseki, Ana Brassard, Kentaro Inui. Context Limitations Make Neural Language Models More Human-Like. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), 16 pages, 2022.
  • Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi and Kentaro Inui. Incorporating Residual and Normalization Layers into Analysis of Masked Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), pp.4547–4568, 2021.

Contact faculty affairs

Interested in working with our renowned faculty?
Fill out the below form and we will get back to you.