RIKEN Center for Advanced Intelligence Project Knowledge Acquisition Team
Team Leader: Yuji Matsumoto (D.Eng.)
Research Summary

A huge amount of knowledge is being produced along with the advance of scientific fields. Such expert knowledge is partly organized in domain databases, but a large portion of it is still kept in scholarly documents. It is time-consuming and cumbersome to construct domain databases and to conduct content-aware retrieval of scholarly documents. The Knowledge Acquisition Team aims at text/figure analysis and knowledge extraction from scholarly documents and also at development of infrastructure for content-aware retrieval of scholarly documents through domain database completion, knowledge organization, relation and summarization technologies.
Research Subjects:
- Natural Language Processing
- Knowledge Acquisition
- Machine Learning
Main Research Fields
- Informatics
Related Research Fields
- Multidisciplinary
- Complex Systems
- Intelligent informatics
Keywords
- Natural Language Processing
- Knowledge Acquisition
- Machine Learning
- Information Extraction
- Information Retrieval
Selected Publications
- 1.
Phi, V-T., Santoso, J., Tran V-H., Shindo H., Shimbo M., Matsumoto, Y.:
"Distant Supervision for Relation Extraction via Piecewise Attention and Bag-Level Contextual Inference"
IEEE Access, Volume:7, Issue:1, pp.103570-103582, (2019). - 2.
Wada T., Iwata T., Matsumoto, Y.:
"Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models"
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), long paper, pp. 3113-3124, (2019). - 3.
Teranishi, H., Shindo H., Matsumoto, Y.:
"Decomposed Local Models for Coordinate Structure Parsing"
Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), long paper, pp.3394-3403, (2019). - 4.
Tran, V-H., Phi, V-T., Shindo H., Matsumoto, Y.:
"Relation Classification Using Segment-Level Attention-based CNN and Dependency-based RNN"
Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), short paper, pp.2793-2798, (2019). - 5.
Liu, J., Shindo, H., Matsumoto, Y.:
"Development of a computer-assisted Japanese functional expression learning system for Chinese-speaking learners"
Educational Technology Research and Development, Springer, Volume:67, Issue:5, pp.1307-1331, (2019). - 6.
Phan, D-A., Matsumoto, Y., Shindo, H.:
"Autoencoder for Semisupervised Multiple Emotion Detection of Conversation Transcripts"
IEEE Transactions on Affective Computing, (2018). - 7.
Ouchi, H., Shindo, H., Matsumoto, Y.:
"A Span Selection Model for Semantic Role Labeling"
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), pp.1630-1642, (2018). - 8.
Phi, V-T., Santoso, J., Shimbo M., Matsumoto, Y.:
"Ranking-Based Automatic Seed Selection and Noise Reduction for Weakly Supervised Relation Extraction"
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL-2018), pp.89–95, (2018). - 9.
Kobayashi, Y., Shimbo, M., Matsumoto, Y.:
Citation Recommendation Using Distributed Representation of Discourse Facets in Scientific Articles
Proceedings of The ACM/IEEE Joint Conference on Digital Libraries (JCDL-2018), pp.243-251, (2018). - 10.
Ouchi, H., Shindo, H., Matsumoto, Y.:
"Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis"
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Volume 1, pp.1591-1600 (2017).
Related Links
Lab Members
Principal investigator
- Yuji Matsumoto
- Team Leader
Core members
- Noriki Nishida
- Postdoctoral Researcher
- Hiroki Teranishi
- Postdoctoral Researcher
- Shanshan Liu
- Technical Staff I
Contact Information
Nihonbashi 1-chome Mitsui Building, 15th floor,
1-4-1 Nihonbashi, Chuo-ku, Tokyo
Tel: +81-(0)3-6225-2482
Fax: +81-(0)3-3271-7202
Email: yuji.matsumoto [at] riken.jp