Multilingual Knowledge Computing Lab.

This is the web page for the collaborative Laboratory of Fujitsu and  Division of Information Science, Nara Institute of Science and Technology.  ( 日本語ページはこちら)
Our research theme is Natural Language Processing (NLP) including basic technologies for constructing knowledge from text such as Named Entity Recognition, Relation Extraction, Entity Resolution, and so on, and NLP applications with constructed knowledge. 

Member
  Tomoya Iwakura (iwakura.tomoya  _at_  fujitsu.com, Professor)
  * Please replace _at_ with @

Alumni
  Kouhei Tsuji (Master Students 2025)
  Xincan Feng (Master Students 2022)

Publications

International Conferences

• Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng and Tomoya Iwakura: SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization. COLING 2025: 1908-1921

• Chunpeng Ma, Aili Shen, Hiyori Yoshikawa, Tomoya Iwakura, Daniel Beck, Timothy Baldwin: On the (In)Effectiveness of Images for Text Classification. EACL 2021: 42-48

• Yutaro Omote, Kyoumoto Matsushita, Tomoya Iwakura, Akihiro Tamura, Takashi Ninomiya: Transformer-based Approach for Predicting Chemical Compound Structures. AACL/IJCNLP 2020: 154-162

• Takuya Makino, Tomoya Iwakura, Hiroya Takamura, Manabu Okumura: Global Optimization under Length Constraint for Neural Text Summarization. ACL (1) 2019: 1039-1048

• Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura: Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing. EMNLP/IJCNLP (1) 2019: 6243-6248

Journal

• Chunpeng Ma, Aili Shen, Hiyori Yoshikawa, Tomoya Iwakura, Daniel Beck, Timothy Baldwin: On the Effectiveness of Images in Multi-modal Text Classification: An Annotation Study. ACM Transactions on Asian and Low-Resource Language Information Processing Volume 22 Issue 3 March 2023 Article No.: 79pp 1–19

• Kanako Komiya, Masaya Suzuki, Tomoya Iwakura, Minoru Sasaki, Hiroyuki Shinnou: Comparison of Methods to Annotate Named Entity Corpora. ACM Trans. Asian Low Resour. Lang. Inf. Process. 17(4): 34:1-34:16 (2018)

• Tomoya Iwakura, Hiroya Takamura, Manabu Okumura: A Named Entity Recognition Method Based on Decomposition and Concatenation of Word Chunks. ACM Trans. Asian Lang. Inf. Process. 12(3): 10:1-10:18 (2013)

Workshops

• Xincan Feng, Zhi Qu, Yuchang Cheng, Taro Watanabe and Nobuhiro Yugami. 2022. Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space. TextGraphs-16.

• Taiki Watanabe, Tomoya Ichikawa, Akihiro Tamura, Tomoya Iwakura, Chunpeng Ma, Tsuneo Kato: Auxiliary Learning for Named Entity Recognition with Multiple Auxiliary Biomedical Training Data. BioNLP@ACL 2022: 130-139

• Resources
  ・BCCWJ Basic Japanese NE corpus