Masahiro Kaneko and Danushka Bollegala (University of Liverpool). Debiasing Pre-trained Contextualised Embeddings.The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL). April, 2021. (accepted)
Masahiro Kaneko and Danushka Bollegala (University of Liverpool). Dictionary-based Debiasing of Pre-trained Word Embeddings.The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL). April, 2021. (accepted)
Kengo Hotate, Masahiro Kaneko and Mamoru Komachi. Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction. In Proceedings of the 28th International Conference on Computational Linguistics (COLING), pp. 2132-2137. December 9, 2020. (paper)
Ryoma Yoshimura, Masahiro Kaneko, Tomoyuki Kajiwara (Osaka University) and Mamoru Komachi. SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction. In Proceedings of the 28th International Conference on Computational Linguistics (COLING), pp. 6516-6522. December 12, 2020. (paper)
Masahiro Kaneko and Danushka Bollegala. Autoencoding Improves Pre-trained Word Embeddings. In Proceedings of the 28th International Conference on Computational Linguistics (COLING), pp. 1699-1713. December 8, 2020. (paper)
Ikumi Yamashita, Satoru Katsumata, Masahiro Kaneko, Aizhan Imankulova and Mamoru Komachi. Cross-lingual Transfer Learning for Grammatical Error Correction. In Proceedings of the 28th International Conference on Computational Linguistics (COLING), pp.4704-4715. December 11, 2020. (paper)
Hongfei Wang, Michiki Kurosawa, Satoru Katsumata and Mamoru Komachi. Chinese Grammatical Correction Using BERT-based Pre-trained Model. In Proceedings of the 1st
Conference of the Asia-Pacific Chapter of the Association for
Computational Linguistics and the 10th International Joint Conference on
Natural Language Processing (AACL-IJCNLP), pp.163-168. December 5, 2020. (paper)
Satoru Katsumata and Mamoru Komachi. Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model. In Proceedings of the 1st
Conference of the Asia-Pacific Chapter of the Association for
Computational Linguistics and the 10th International Joint Conference on
Natural Language Processing (AACL-IJCNLP), pp. 827-832. December 6, 2020. (paper)
Siti Oryza Khairunnisa, Aizhan Imankulova and Mamoru Komachi. Towards a Standardized Dataset on Indonesian Named Entity Recognition. In Proceedings of the 1st
Conference of the Asia-Pacific Chapter of the Association for
Computational Linguistics and the 10th International Joint Conference on
Natural Language Processing: Student Research Workshop (AACL-IJCNLP SRW 2020), pp.64-71. December 7, 2020. (paper)
Mana Ashida, Seunghun Lee (International Christian University) and Kunzang Mamgyal (NBDD Colledge). Building a Part-of-Speech Tagged Corpus for Drenjongke (Bhutia). In Proceedings of the 1st
Conference of the Asia-Pacific Chapter of the Association for
Computational Linguistics and the 10th International Joint Conference on
Natural Language Processing: Student Research Workshop (AACL-IJCNLP SRW 2020), pp.57-63. December 7, 2020. (paper)
Hiroki Homma and Mamoru Komachi. Non-Autoregressive Grammatical Error Correction Towards a Writing Support System. In Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Application (NLP-TEA), pp.1-10. December 4, 2020. (paper)
Hongfei Wang and Mamoru Komachi. TMU-NLP System Using BERT-based Pre-trained Model to the NLP-TEA CGED Shared Task 2020. In Proceedings of the 6th Workshop on Natural Language Processing (NLP-TEA), pp.87-90. December 4, 2020. (paper)
Zizheng Zhang, Tosho Hirasawa, Wei Houjing, Masahiro Kaneko and Mamoru Komachi. Translation of New Named Entities from English to Chinese. In Proceedings of the 7th Workshop on Asian Translation (WAT), pp.58-63. December 4, 2020. (paper)
Hiroto Tamura, Tosho Hirasawa, Masahiro Kaneko and Mamoru Komachi. TMU Japanese-English Multimodal Machine Translation System for WAT 2020. In Proceedings of the 7th Workshop on Asian Translation (WAT), pp. 80-91. December, 2020. (paper)
Hwichan Kim, Tosho Hirasawa and Mamoru Komachi. Korean to Japanese Neural Machine Translation System Using Hanja Information. In Proceedings of the 7th Workshop on Asian Translation (WAT), pp. 127-134. December, 2020. (paper)
2020/12/03 以下の論文を音声言語および自然言語処理シンポジウムにて発表しました。
安道健一郎(東京都立大/理研)・奥村貴史(北見工大/理研)・小町守(東京都立大)・堀口裕正 (国立病院機構)・松本裕治(理研). 診療録解析のための文のセグメント分割と意味ラベル付与. 情報処理学会第246回自然言語処理研究会. December 3, 2020.
2020/11/20 以下の論文を Conference on Machine Translation (WMT) にて発表しました。
Aizhan Imankulova, Masahiro Kaneko, Tosho Hirasawa and Mamoru Komachi. Towards Multimodal Simultaneous Neural Machine Translation. In 2020 Fifth Conference on Machine Translation (WMT). November, 2020.
Akifumi Nakamachi (Osaka University), Hiroki Shimanaka, Tomoyuki Kajiwara (Osaka University) and Mamoru Komachi. TMUOU submission for WMT20 Quality Estimation Shared Task. In 2020 Fifth Conference on Machine Translation (WMT 2020). November, 2020.
2020/11/16 以下の論文が ACM TALLIP に採択されました。
Longtu Zhang and Mamoru Komachi. Using Sub-Character Level Information for Neural Machine Translation of Logographic Languages. ACM Transaction on Asian and Low-Resource Language Information Processing. (accepted)
2020/11/05 以下の研究をオンライン発表しました。
Yuting Zhao, Mamoru Komachi, Tomoyuki Kajiwara (Osaka University), Chenhui Chu (Osaka University). Double Attention-based Multimodal Neural Machine Translation with Semantic Image Regions. In The 22nd Annual Conference of the European Association for Machine Translation (EAMT 2020), pp.105-114. Lisbon, Portugal. November, 2020.
2020/09/30 情報処理学会自然言語処理研究会にて以下の発表をしました。
本間広樹, 小町守. 非自己回帰モデルを用いた高速な日本語文法誤り訂正. 情報処理学会第245回自然言語処理研究会. September 30, 2020.
安道健一郎, 関根聡(理化学研究所), 小町守. Wikipedia における読者属性を考慮した引用要否の分析. 情報処理学会第245回自然言語処理研究会. September 30, 2020.
2020/07/10 自然言語処理のトップカンファレンス、The 58th Annual Meeting of Association for Computational Linguistics (ACL 2020) および関連ワークショップにて、以下の発表を行いました。
Hwichan Kim, Tosho Hirasawa and Mamoru Komachi. Zero-shot North Korean to English Neural Machine Translation by Character Tokenization and Phoneme Decomposition. In Proceedings of the 58th Annual Meeting of the Association for
Computational Linguistics: Student Research Workshop (ACL 2020 SRW), pp.72-78. July, 2020. (paper)
Yujin Takahashi, Satoru Katsumata and Mamoru Komachi. Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner's Error Tendency. In Proceedings
of the 58th Annual Meeting of the Association for Computational
Linguistics: Student Research Workshop (ACL 2020 SRW), pp.27-32. July, 2020. (paper)
Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki and Kentaro Inui. Can Encoder-decoder Models Benefit from Pre-trained LanguageRepresentation in Grammatical Error Correction? In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp.4258-4254. July, 2020. (paper)
Masahiro Kaneko, Aizhan Imankulova, Tosho Hirasawa and Mamoru Komachi. English-to-Japanese Diverse Translation Using Opposite Direction Models. In Proceedings of The 4th Workshop on Neural Generation and Translation (WNGT 2020), pp.134-138. July, 2020. (paper)
Tosho Hirasawa, Zhishen Yang, Mamoru Komachi and Naoaki Okazaki. Keyframe Segmentation and Positional Encoding for Video-guided Machine Translation Challenge 2020. In Workshop on Advances in Language and Vision Research. July, 2020. (paper)