Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Named Entity Recognition and Relation Extraction Using Enhanced Table Filling by Contextualized Representations

Youmi Ma, Tatsuya Hiraoka, Naoaki Okazaki.
Journal of Natural Language Processing, vol. 29, No. 1, pages 187-223, 2022

単語分割と後段モデルの損失値を用いた同時最適化

English title: Joint Optimization of Word Segmentation and Downstream Model using Downstream Loss

平岡達也, 高瀬翔, 内海慶, 欅惇志, 岡崎直観.
Journal of Natural Language Processing, vol. 29, No. 1, pages 112-143, 2022

Recurrent Neural Hidden Markov Model for High-Order Transition

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki.
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP). Volume 21, Issue 2, Article No.: 36, pp: 1-15, 2021

テキストベクトルの重みづけを用いたタスクに対する単語分割の最適化

English title: Optimizing Word Segmentation for Downstream Tasks by Weighting Text Vector

平岡達也, 高瀬翔, 内海慶, 欅惇志, 岡崎直観.
Journal of Natural Language Processing, vol. 28, No. 2, pages 479-507, 2021

最優秀論文賞 / First-place Best Paper Award

Conference/Workshop Papers

RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles

Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Velibor Bojkovic, Benjamin Heinzerling, Hilal Alqaubeh, Martin Takáč, Kentaro Inui.
In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025

Repetition Neurons: How Do Language Models Produce Repetitions?

Tatsuya Hiraoka, Kentaro Inui.
In 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025

The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces

Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui.
In 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025

SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization

Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Tomoya Iwakura.
The 31st International Conference on Computational Linguistics, 2025

An Analysis of BPE Vocabulary Trimming in Neural Machine Translation

Marco Cognetta, Tatsuya Hiraoka, Rico Sennrich, Yuval Pinter, Naoaki Okazaki.
In Proceedings of the Fifth Workshop on Insights from Negative Results in NLP, pages 48–50, Mexico City, Mexico, 2024

Vocabulary Replacement in SentencePiece for Domain Adaptation

Teruno Kajiura, Shiho Takano, Tatsuya Hiraoka, Kimio Kuramitsu.
In Proceedings of The 37th Pacific Asia Conference on Language, Information and Computation (PACLIC 37), 2023

MaxMatch-Dropout: Subword Regularization for WordPiece

Tatsuya Hiraoka.
In Proceedings of the 29th International Conference on Computational Linguistics (COLING), pages 4864-4872, Gyeongju, Republic of Korea, 2022

Joint Entity and Relation Extraction Based on Table Labeling Using Convolutional Neural Networks

Youmi Ma, Tatsuya Hiraoka, Naoaki Okazaki.
In 6th Workshop on Structured Prediction for NLP (SPNLP), pages 11-21, 2022

Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation

Sho Takase, Tatsuya Hiraoka, Naoaki Okazaki.
In Findings of the Association for Computational Linguistics: ACL 2022, pages 2536–2541, 2022

Word-level Perturbation Considering Word Length and Compositional Subwords

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki.
In Findings of the Association for Computational Linguistics: ACL 2022, pages 3268-3275, 2022

Joint Optimization of Tokenization and Downstream Model

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki.
In Findings of the Association for Computational Linguistics: ACL 2021, Association for Computational Linguistics, pages 244–255, 2021

Optimizing Word Segmentation for Downstream Task

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki.
In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pages 1341–1351, 2020

Stochastic Tokenization with a Language Model for Neural Text Classification

Tatsuya Hiraoka, Hiroyuki Shindo, Yuji Matsumoto.
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1620–1629, 2019

Non-refereed Papers

Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Characters

Tatsuya Hiraoka, Kentaro Inui.
arXiv, 2025

Bit-level BPE: Below the byte boundary

Sangwhan Moon, Tatsuya Hiraoka, Naoaki Okazaki.
arXiv, 2025

Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance

Shintaro Ozaki, Tatsuya Hiraoka, Hiroto Otake, Hiroki Ouchi, Masaru Isonuma, Benjamin Heinzerling, Kentaro Inui, Taro Watanabe, Yusuke Miyao, Yohei Oseki, Yu Takagi.
arXiv, 2025

知識汚染パラメータの枝刈りによる関係知識推論の改善

金輝燦, 金子正弘, 平岡達也, 小町守, 乾健太郎, TIMOTHY Baldwin.
2025年度人工知能学会全国大会（第39回）, 2025

言語で柔軟に操作可能なWhat-if社会シミュレータ

English title: What-if social simulator that can be flexibly operated with natural language

山田広明, 山田寛章, 平岡達也.
第26回人工知能学会第二種研究会　ビジネス・インフォマティクス研究会, 2025

2024年度人工知能学会研究会優秀賞 / JSAI Incentive Award

思考発話を利用した個人の発話及び性格特性再現

石倉誠也, 山田寛章, 平岡達也, 山田広明, 徳永健伸.
言語処理学会第29回年次大会 (NLP2025), pp. 4155-4160, 2025

思考発話を利用した個人の発話及び性格特性再現

石倉誠也, 山田寛章, 平岡達也, 山田広明, 徳永健伸.
言語処理学会第29回年次大会 (NLP2025), pp. 4155-4160, 2025

大規模言語モデルにおけるペルソナの役割と内部動作の理解

尾崎慎太郎, 平岡達也, 大竹啓永, 大内啓樹, 渡辺太郎, 宮尾祐介, 大関洋平, 高木優.
言語処理学会第29回年次大会 (NLP2025), pp. 2648-2653, 2025

誤字に対するTransformerベースLLMのニューロンおよびヘッドの役割調査

辻航平, 平岡達也, 鄭育昌, 荒牧英治, 岩倉友哉.
言語処理学会第29回年次大会 (NLP2025), pp. 645-650, 2025

Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors

Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Eiji Aramaki, Tomoya Iwakura.
arXiv, 2025

Number Representations in LLMs: A Computational Parallel to Human Perception

H.V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic, Tatsuya Hiraoka, Ahmed Oumar El-Shangiti, Munachiso Nwadike, Kentaro Inui.
arXiv, 2025

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

LLM-jp (Akiko Aizawa, Eiji Aramaki, Bowen Chen, Fei Cheng, Hiroyuki Deguchi, Rintaro Enomoto, Kazuki Fujii, Kensuke Fukumoto, Takuya Fukushima, Namgi Han, Yuto Harada, Chikara Hashimoto, Tatsuya Hiraoka, Shohei Hisada, Sosuke Hosokawa, Lu Jie, Keisuke Kamata, Teruhito Kanazawa, Hiroki Kanezashi, Hiroshi Kataoka, Satoru Katsumata, Daisuke Kawahara, Seiya Kawano, Atsushi Keyaki, Keisuke Kiryu, Hirokazu Kiyomaru, Takashi Kodama, Takahiro Kubo, Yohei Kuga, Ryoma Kumon, Shuhei Kurita, Sadao Kurohashi, Conglong Li, Taiki Maekawa, Hiroshi Matsuda, Yusuke Miyao, Kentaro Mizuki, Sakae Mizuki, Yugo Murawaki, Akim Mousterou, Ryo Nakamura, Taishi Nakamura, Kouta Nakayama, Tomoka Nakazato, Takuro Niitsuma, Jiro Nishitoba, Yusuke Oda, Hayato Ogawa, Takumi Okamoto, Naoaki Okazaki, Yohei Oseki, Shintaro Ozaki, Koki Ryu, Rafal Rzepka, Keisuke Sakaguchi, Shota Sasaki, Satoshi Sekine, Kohei Suda, Saku Sugawara, Issa Sugiura, Hiroaki Sugiyama, Hisami Suzuki, Jun Suzuki, Toyotaro Suzumura, Kensuke Tachibana, Yu Takagi, Kyosuke Takami, Koichi Takeda, Masashi Takeshita, Masahiro Tanaka, Kenjiro Taura, Arseny Tolmachev, Nobuhiro Ueda, Zhen Wan, Shuntaro Yada, Sakiko Yahata, Yuya Yamamoto, Yusuke Yamauchi, Hitomi Yanaka, Rio Yokota, Koichiro Yoshino).
arXiv, 2024

Non-refereed Presentations

SubRegWeigh: サブワード正則化による高速アノテーション補正

辻航平, 平岡達也, 鄭育昌, 岩倉友哉.
第19回NLP若手の会シンポジウム, 2024

内心描写付きの対話データを用いた非著名人の性格特性再現

石倉誠也, 山田寛章, 平岡達也, 山田広明, 徳永健伸.
第19回NLP若手の会シンポジウム, 2024

企業情報を考慮した広告文の自動生成

昇夏海, 平岡達也, 丹羽彩奈, 岡﨑直観, 脇本宏平, 黒田和矢, 西口佳佑.
第15回NLP若手の会シンポジウム, 2020

RNNによる遷移確率計算を用いた隠れマルコフモデル

平岡達也, 高瀬翔, 岡崎直観.
第14回NLP若手の会シンポジウム, 2019

ネットスラング『なう』についての統語論的考察

平岡達也.
日本英語教育学会・日本教育言語学会第47回年次研究集会, 2017

Ph.D in Engineering