Koichi Nagatsuka

According to our database, Koichi Nagatsuka authored at least 7 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation.

Natsuo Yamashita, Koichi Nagatsuka, Hiroaki Kokubo, Kota Dohi, Tuan Vu Ho

CoRR, March, 2026

Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks.

Masaya Tsunokake, Yuta Koreeda, Terufumi Morishita, Koichi Nagatsuka, Hikaru Tomonari, Yasuhiro Sogawa

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

2025

A Nested Watermark for Large Language Models.

Koichi Nagatsuka, Terufumi Morishita, Yasuhiro Sogawa

CoRR, June, 2025

2023

Length-Based Curriculum Learning for Efficient Pre-training of Language Models.

Koichi Nagatsuka, Clifford Broni-Bediako, Masayasu Atsumi

New Gener. Comput., March, 2023

2022

Prediction and Analysis of Drug-Glycoprotein Interactions with Mutual Attention Neural Networks.

Eiji Shinkawa, Koichi Nagatsuka, Yuki Murata, Tamiko Ono, Masae Hosoda, Kiyoko F. Aoki-Kinoshita, Masayasu Atsumi

Proceedings of the Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, 2022

2021

Pre-training a BERT with Curriculum Learning by Increasing Block-Size of Input Text.

Koichi Nagatsuka, Clifford Broni-Bediako, Masayasu Atsumi

Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), 2021

2018

Paraphrase Identification for Twitter by Co-Training Based on Words and Characters.

Koichi Nagatsuka, Masayasu Atsumi

Proceedings of the 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS), 2018