Makoto MIWA
Professor in the Department of Advanced Science and Technology at Toyota Technological Institute, Japan.
Leading the Knowledge and Data Engineering
(KDE) Laboratory.
Research Interests
Natural Language Processing
Information extraction, event/relation extraction, representation learning, large/diffusion language models, and sign language processing.
Machine/Deep Learning
Diffusion, sequence-to-sequence learning, transfer learning, and multimodal graph representation learning.
Bio-Medical Text Mining
Designing annotated corpora, information extraction systems leveraging external knowledge.
Artificial Intelligence in Games
Optimizing static evaluation functions, reinforcement learning, and search algorithms for computer game players (e.g., Shogi).
Software/Services
Selected Publications
View Full List β-
ACL 2026 Recent
Reviving Iterative Refinement in Diffusion-based NER with an Initializer-Restorer Approach
In the Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026, Volume 2: Short Papers), pp. 877β882, July 2026. -
EACL 2026 Recent
Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation
In the Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), pp. 6678β6692, March 2026. -
ACL 2025
Enhancing NER by Harnessing Multiple Datasets with Conditional Variational Autoencoders
In the Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025, Volume 2: Short Papers), pp. 1107β1117, July 2025. -
ACL 2016
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
In the Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016, Volume 1: Long Papers), pp. 1105β1116, August 2016. -
EMNLP 2014
Modeling Joint Entity and Relation Extraction with Table Representation
In the Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), pp. 1858β1869, October 2014. -
Bioinformatics
Integrating heterogeneous knowledge graphs into drug-drug interaction extraction from the literature
Bioinformatics, Vol. 39, Issue 1, btac754, January 2023.
Contact Information
π Office Address:
Toyota Technological Institute
2-12-1 Hisakata, Tempaku-ku, Nagoya, 468-8511, Japan
βοΈ Email Address:
makoto-miwa at toyota-ti.ac.jp