Centers & Labs

Home > Research > Centers & Labs > RIKEN Center for Advanced Intelligence Project > Goal-Oriented Technology Research Group >

RIKEN Center for Advanced Intelligence Project

Natural Language Understanding Team

Team Leader: Kentaro Inui (D.Eng.)
Kentaro  Inui(D.Eng.)

In recent years, research on natural language processing has developed greatly in parallel with the distribution of huge language data and advances in machine learning and deep learning. However, a number of breakthroughs are still necessary for developing artificial intelligence that "understands" a language. At the Natural Language Understanding Team, we will conduct research on fundamental technologies for understanding languages by computers through by creating new tasks for automatic assessment of human language activities, such as reviewing argumentation and descriptive responses in pedagogical contexts. We aim to extend upon the frontier of language processing in both basic research and applied research while collaborating with the Language Information Access Technology Team and other teams in the Generic Technology Research Group.

Main Research Field

Computer Science

Research Subjects

  • Natural Language Processing

Selected Publications

Papers with an asterisk(*) are based on research conducted outside of RIKEN.
  1. *Sho Yokoi, Daichi Mochihashi, Ryo Takahashi, Naoaki Okazaki, and Kentaro Inui:
    "Learning Co-Substructures by Kernel Dependence Maximization"
    Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), to appear (2017).
  2. *Akira Sasaki, Kazuaki Hanawa, Naoaki Okazaki and Kentaro Inui:
    "Other Topics You May Also Agree or Disagree: Modeling Inter-Topic Preferences using Tweets and Matrix Factorization"
    Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), to appear (2017).
  3. *Ran Tian, Naoaki Okazaki, Kentaro Inui:
    "The Mechanism of Additive Composition"
    Machine Learning, pp.1-48, in press (2017).
  4. *Koji Matsuda, Akira Sasaki, Naoaki Okazaki and Kentato Inui:
    "Geographical Entity Annotated Corpus of Japanese Microblogs"
    Journal of Information Processing Vol. 25, pp.121-130 (2017).
  5. *Sho Takase, Naoaki Okazaki and Kentaro Inui:
    "Modeling semantic compositionality of relational patterns"
    Engineering Applications of Artificial Intelligence, vol.50, pp.256-264 (2016).
  6. *Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui and Sebastian Riedel:
    "Neural Architectures for Fine-grained Entity Type Classification"
    Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp.1271-1280 (2017).
  7. *Naoya Inoue, Yuichiro Matsubayashi, Masayuki Ono, Naoaki Okazaki and Kentaro Inui:
    "Modeling Context-sensitive Selectional Preference with Distributed Representations"
    Proceedings of the 26th International Conference on Computational Linguistics (COLING), pp.2829-2838 (2016).
  8. *Sho Takase, Naoaki Okazaki and Kentaro Inui:
    "Composing Distributed Representations of Relational Patterns"
    Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), pp.2276-2286 (2016).
  9. *Ran Tian, Naoaki Okazaki and Kentaro Inui:
    "Learning Semantically and Additively Compositional Distributional Representations"
    Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), pp.1277-1287 (2016).
  10. *Sosuke Kobayashi, Ran Tian, Naoaki Okazaki and Kentaro Inui:
    "Dynamic Entity Representation with Max-pooling Improves Machine Reading"
    Proceedings of the North American Chapter of the Association for Computational Linguistics and Human Language Technologies (NAACL-HLT), pp.850-855 (2016).

Contact information

6-3-09, Aoba, Aramaki, Aoba-ku,
Sendai, 980-8579, Japan
Tel: +81-(0)22-795-7091
Fax: +81-(0)22-795-4285

Email: inui [at] ecei.tohoku.ac.jp

Home > Research > Centers & Labs > RIKEN Center for Advanced Intelligence Project > Goal-Oriented Technology Research Group >