Hiroyuki Deguchi

Orcid: 0000-0003-2127-6607

Affiliations:
  • Nippon Telegraph and Telephone, Tokyo, Japan
  • Nara Institute of Science and Technology, Ikoma, Japan


According to our database1, Hiroyuki Deguchi authored at least 23 papers between 2019 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Case-Based Decision-Theoretic Decoding with Quality Memories.
J. Nat. Lang. Process., 2026

Hacking Neural Evaluation Metrics with Single Text.
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Hacking Neural Evaluation Metrics with Single Hub Text.
CoRR, December, 2025

NTTSU at WMT2025 General Translation Task.
Proceedings of the Tenth Conference on Machine Translation, 2025

Long-Tail Crisis in Nearest Neighbor Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

Agreement-Constrained Probabilistic Minimum Bayes Risk Decoding.
Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Case-Based Decision-Theoretic Decoding with Quality Memories.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024
Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding.
CoRR, 2024

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs.
CoRR, 2024

Document-level Translation with LLM Reranking: Team-J at WMT 2024 General Translation Task.
Proceedings of the Ninth Conference on Machine Translation, 2024

mbrs: A Library for Minimum Bayes Risk Decoding.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

Detector-Corrector: Edit-Based Automatic Post Editing for Human Post Editing.
Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), 2024

Centroid-Based Efficient Minimum Bayes Risk Decoding.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
knn-seq: Efficient, Extensible kNN-MT Framework.
CoRR, 2023

NAIST-NICT WMT'23 General MT Task Submission.
Proceedings of the Eighth Conference on Machine Translation, 2023

Subset Retrieval Nearest Neighbor Machine Translation.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022
NAIST-NICT-TIT WMT22 General MT Task Submission.
Proceedings of the Seventh Conference on Machine Translation, 2022

2021
Synchronous Syntactic Attention for Transformer Neural Machine Translation.
Proceedings of the ACL-IJCNLP 2021 Student Research Workshop, 2021

2020
Bilingual Subword Segmentation for Neural Machine Translation.
Proceedings of the 28th International Conference on Computational Linguistics, 2020

2019
Dependency-Based Self-Attention for Transformer NMT.
Proceedings of the International Conference on Recent Advances in Natural Language Processing, 2019


  Loading...