| Encoder-decoder models can benefit from pre-trained masked language models in grammatical error correction M Kaneko, M Mita, S Kiyono, J Suzuki, K Inui arXiv preprint arXiv:2005.00987, 2020 | 124 | 2020 |
| Gender-preserving debiasing for pre-trained word embeddings M Kaneko, D Bollegala arXiv preprint arXiv:1906.00742, 2019 | 113 | 2019 |
| Debiasing pre-trained contextualised embeddings M Kaneko, D Bollegala arXiv preprint arXiv:2101.09523, 2021 | 79 | 2021 |
| Multi-head multi-layer attention to deep language representations for grammatical error detection M Kaneko, M Komachi Computación y Sistemas 23 (3), 883-891, 2019 | 36 | 2019 |
| Unmasking the mask–evaluating social biases in masked language models M Kaneko, D Bollegala Proceedings of the AAAI Conference on Artificial Intelligence 36 (11), 11954 …, 2022 | 32 | 2022 |
| Dictionary-based debiasing of pre-trained word embeddings M Kaneko, D Bollegala arXiv preprint arXiv:2101.09525, 2021 | 32 | 2021 |
| Grammatical Error Detection Using Error-and Grammaticality-Specific Word Embeddings M Kaneko, Y Sakaizawa, M Komachi Proceedings of the Eighth International Joint Conference on Natural Language …, 2017 | 32 | 2017 |
| Gender bias in masked language models for multiple languages M Kaneko, A Imankulova, D Bollegala, N Okazaki arXiv preprint arXiv:2205.00551, 2022 | 21 | 2022 |
| Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models---Is Single-Corpus Evaluation Enough? M Mita, T Mizumoto, M Kaneko, R Nagata, K Inui arXiv preprint arXiv:1904.02927, 2019 | 21 | 2019 |
| TMU transformer system using BERT for re-ranking at BEA 2019 grammatical error correction on restricted track M Kaneko, K Hotate, S Katsumata, M Komachi Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building …, 2019 | 17 | 2019 |
| Debiasing isn't enough!--On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks M Kaneko, D Bollegala, N Okazaki arXiv preprint arXiv:2210.02938, 2022 | 14 | 2022 |
| Interpretability for language learners using example-based grammatical error correction M Kaneko, S Takase, A Niwa, N Okazaki arXiv preprint arXiv:2203.07085, 2022 | 14 | 2022 |
| Sentence concatenation approach to data augmentation for neural machine translation S Kondo, K Hotate, M Kaneko, M Komachi arXiv preprint arXiv:2104.08478, 2021 | 14 | 2021 |
| SOME: Reference-less sub-metrics optimized for manual evaluations of grammatical error correction R Yoshimura, M Kaneko, T Kajiwara, M Komachi Proceedings of the 28th International Conference on Computational …, 2020 | 13 | 2020 |
| Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings Y Zhou, M Kaneko, D Bollegala arXiv preprint arXiv:2203.07523, 2022 | 11 | 2022 |
| Generating diverse corrections with local beam search for grammatical error correction K Hotate, M Kaneko, M Komachi Proceedings of the 28th International Conference on Computational …, 2020 | 11 | 2020 |
| Autoencoding improves pre-trained word embeddings M Kaneko, D Bollegala arXiv preprint arXiv:2010.13094, 2020 | 10 | 2020 |
| A self-refinement strategy for noise reduction in grammatical error correction M Mita, S Kiyono, M Kaneko, J Suzuki, K Inui arXiv preprint arXiv:2010.03155, 2020 | 10 | 2020 |
| Towards multimodal simultaneous neural machine translation A Imankulova, M Kaneko, T Hirasawa, M Komachi arXiv preprint arXiv:2004.03180, 2020 | 10 | 2020 |
| TMU system for SLAM-2018 M Kaneko, T Kajiwara, M Komachi Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building …, 2018 | 10 | 2018 |
Mamoru KomachiProfessor at Hitotsubashi UniversityVerified email at r.hit-u.ac.jp
