Home

Natural language processing and computational linguistics research group at the Tokyo Metropolitan University. We aim at creating a research hub for natural language processing in Tokyo.

Keywords

natural language processing (machine translation, error correction/detection, information extraction, semantic analysis), web mining, machine learning (deep learning, representation learning)

News

  • 2018/05/11 Our paper will be presented at The 56th Annual Meeting of the Association for Computational Linguistics. See you in Melbourne!
    • Satoru Katsumata, Yukio Matsumura, Hayahide Yamagishi and Mamoru Komachi. Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Model. In Proceedings of ACL 2018 Student Research Workshop. Melbourne, Australia. July, 2018
  • 2018/05/01 Our papers will be presented at The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. See you in New Orleans!
    • Michiki Kurosawa, Yukio Matsumura, Hayahide Yamagishi and Mamoru Komachi. Japanese Predicate Conjugation for Neural Machine Translation. In Proceedings of NAACL 2018 Student Research Workshop. June 2, 2018.
    • Hiroki Shimanaka, Tomoyuki Kajiwara and Mamoru Komachi. Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations. In Proceedings of NAACL 2018 Student Research Workshop. June 2, 2018.
    • Masahiro Kaneko, Tomoyuki Kajiwara and Mamoru Komachi. TMU System for SLAM-2018. In Proceedings of The 13th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2018): Shared Task on Second Language Acquisition Modeling. June 5, 2018.
    • Tomoyuki Kajiwara and Mamoru Komachi. Complex Word Identification Based on Frequency in a Learner Corpus. In Proceedings of The 13th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2018): Shared Task on Complex Word Identification. June 5, 2018.
  • 2018/02/13 Our papers were accepted at the 11th Edition of the Language Resources and Evaluation Conference (LREC) and its collocated workshop, 2nd Workshop on Text Analysis for Cybersecurity and Online Safety (TA-COS)!
    • Yuya Sakaizawa and Mamoru Komachi. Construction of a Japanese Word Similarity Dataset. In Proceedings of the 11th Edition of the Language Resources and Evaluation Conference (LREC). May 10, 2018.
    • Sirihattasak Sugan, Mamoru Komachi and Hiroshi Ishikawa. Annotation and Classification of Toxicity for Thai Twitter. In Proceedings of the 2nd Workshop on Text Analysis for Cybersecurity and Online Safety (TA-COS). May 12, 2018.
  • 2017/10/01 Our papers were accepted at the workshops of the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017)!
    • Kento Shioda, Mamoru Komachi, Rue Ikeya (ROIS) and Daichi Mochihashi (ISM). Suggesting Sentences for ESL using Kernel Embeddings. NLPTEA 2017.
    • Aizhan Imankulova, Takayuki Sato and Mamoru Komachi. Improving Low-Resource Neural Machine Translation with Filtered Pseudo-Parallel Corpora. WAT 2017.
    • Yuuki Sekizawa, Tomoyuki Kajiwara and Mamoru Komachi. Improving Japanese-English Neural Machine Translation by Paraphrasing the Target Language. WAT 2017.
  • 2017/09/25 We published following paper on arXiv.
    • Yoshiaki Kitagawa and Mamoru Komachi. Long-Short Term Memory for Japanese Word Segmentation. In arXiv e-prints, 1709.08011 (10 pages). September 2017. (paper)
  • 2017/09/14 Our papers were accepted at The 8th International Joint Conference on Natural Language Processing (IJCNLP 2017)!
    • Masahiro Kaneko, Yuya Sakaizawa, Mamoru Komachi. Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings. IJCNLP 2017. (long paper)
    • Tomoyuki Kajiwara, Mamoru Komachi, Daichi Mochihashi (Institute of Statistical Mathematics). MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting. IJCNLP 2017. (long paper)
    • Hayahide Yamagishi, Shin Kanouchi, Takayuki Sato, Mamoru Komachi. Improving Japanese-to-English Neural Machine Translation by Voice Prediction. IJCNLP 2017. (short paper)
    • Tomoyuki Kajiwara and Atsushi Fujita (National Institute of Information and Communications Technology). Semantic Features based on Word Alignments for Estimating Quality of Text Simplification. IJCNLP 2017. (short paper)
  • 2017/07/31 We released Tokyo Metropolitan University Paraphrase Corpus (TMUP).
  • 2017/06/27 We published following paper on arXiv.
    • Yukio Matsumura, Takayuki Sato and Mamoru Komachi. English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor. In arXiv e-prints, 1706.08198 (8 pages). June 2017.
  • 2017/05/23 Our paper will be presented at 2017 ACL Student Research Workshop. See you in Vancouver!
    • Yui Suzuki, Tomoyuki Kajiwara and Mamoru Komachi. Building a Non-Trivial Paraphrase Corpus using Multiple Machine Translation Systems. In ACL 2017 Student Research Workshop.  August 2017. (to appear)
  • 2017/04/05 We published following papers on arXiv.
    • Ryosuke Miyazaki and Mamoru Komachi. Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention. In arXiv e-prints, 1704.00924 (6 pages). April 2017. (paper)
    • Junki Matsuo, Mamoru Komachi and Katsuhito Sudoh. Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings. In arXiv e-prints, 1704.00380 (5 pages). April 2017. (paper)
  • 2017/04/04 New members joined our lab!
    • Masters students: S. Sugan, Makoto Takenaka and Ryosuke Shirai.
    • Undergraduates: Yota Osanai, Naruhisa Shirai, Michiki Kurosawa, Hiroki Shimanaka and Satoru Katsumata
    • Research student: Kohei Akiyama and Mio Arai
  • 2017/03/20 We published following paper on arXiv.
    • Yuya Sakaizawa and Mamoru Komachi. Construction of a Japanese Word Similarity Dataset. In arXiv e-prints, 1703.05916 (5 pages). March 2017.
  • 2017/03/16 We published following paper on arXiv.
    • Ai Hirata and Mamoru Komachi. Sparse Named Entity Classification using Factorization Machines. In arXiv e-prints, 1703.04879 (5 pages). March 2017.
Subpages (1): News