- Journal: 'Massive Exploration of Pseudo Data for Grammatical Error Correction', IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- International Conference: 'Efficient Construction of Model Family through Progressive Training Using Model Expansion', Second Conference on Language Modeling, 2025
- International Conference: 'Spike No More: Stabilizing the Pre-training of Large Language Models', Second Conference on Language Modeling, 2025
- International Conference: 'Large Vocabulary Size Improves Large Language Models', Findings of the Association for Computational Linguistics: ACL 2025, 2025
- International Conference: 'Bridging the Gap between Subword and Character Segmentation in Pretrained Language Models', Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, 2023
- International Conference: 'B2T Connection: Serving Stability and Performance in Deep Transformers', Findings of the Association for Computational Linguistics: ACL 2023, 2023
- International Conference: 'Lessons on Parameter Sharing across Layers in Transformers', Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), 2023
- International Conference: 'NT5 at WMT 2022 General Translation Task', Proceedings of the Seventh Conference on Machine Translation (WMT), 2022
- International Conference: 'SHAPE: Shifted Absolute Position Embedding for Transformers', Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021
- International Conference: 'Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution', Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021
- International Conference: 'Rethinking Perturbations in Encoder-Decoders for Fast Training', Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, 2021
Research Experience
- Oct 2023 - Present, SB Intuitions Co., Ltd.
- Oct 2023 - Jun 2024, LINE Yahoo Corporation (LY Corporation)
- Aug 2022 - Sep 2023, LINE Corporation
- Apr 2019 - Jul 2022, RIKEN Center for Advanced Intelligence Project: Natural Language Understanding Team
Education
- Doctoral program, Graduate School of Information Sciences, Tohoku University, Oct 2020 - Mar 2022, Advisors: Kentaro Inui and Jun Suzuki
- Master's program, Graduate School of Information Sciences, Tohoku University, Apr 2017 - Mar 2019, Advisors: Kentaro Inui and Jun Suzuki
- Bachelor's degree, Department of Information and Intelligent Systems, Tohoku University, Apr 2013 - Mar 2017, Advisor: Kentaro Inui
Background
Research interests include natural language processing and machine learning. Specializes in information science.
Miscellany
Personal website provides links to Google Scholar and GitHub