Publications

Google Scholar · DBLP · ResearchGate · ACL Anthology

Preprints

2026

  1. arXiv
    Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation
    arXiv preprint, 2026
  2. arXiv
    ExCAM: Explainable Cultural Awareness Metrics
    arXiv preprint, 2026
  3. arXiv
    optimer.png
    OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
    Haiyue Song and Masao Utiyama
    arXiv preprint, 2026
  4. arXiv
    Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
    Boxuan Lyu, Haiyue Song, and Zhi Qu
    arXiv preprint, 2026

2025

  1. arXiv
    Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation
    arXiv preprint, 2025
  2. arXiv
    When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models
    Ahmed Elshabrawy, Hour Kaing, Haiyue Song, Alham Fikri Aji, Hideki Tanaka, Masao Utiyama, and Raj Dabre
    arXiv preprint, 2025
  3. arXiv
    IteRABRe: Iterative Recovery-Aided Block Reduction
    arXiv preprint, 2025

Journal Articles

2024

  1. JIP
    Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts
    Journal of Information Processing, 2024
  2. JNLP
    diverseg.png
    DiverSeg: Leveraging Diverse Segmentations with Cross-granularity Alignment for Neural Machine Translation
    Journal of Natural Language Processing, 2024

2023

  1. TALLIP
    selfseg.png
    SelfSeg: A Self-Supervised Sub-Word Segmentation Method for Neural Machine Translation
    ACM Transactions on Asian and Low-Resource Language Information Processing, Aug 2023
  2. JIP
    Spatial Hierarchical Attention Network Based Video-guided Machine Translation
    Weiqi Gu, Haiyue Song, Chenhui Chu, and Sadao Kurohashi
    Journal of Information Processing, 2023

2019

  1. TODAES
    Energy-Efficient and Quality-Assured Approximate Computing Framework Using a Co-Training Method
    Li Jiang, Zhuoran Song, Haiyue Song, Chengwen Xu, Qiang Xu, Naifeng Jing, Weifeng Zhang, and Xiaoyao Liang
    ACM Transactions on Design Automation of Electronic Systems, Aug 2019

International Conferences

2025

  1. IJCNLP-AACL
    formatrl.png
    Structured Document Translation via Format Reinforcement Learning
    In 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, acceptance rate 19% , Dec 2025
  2. IJCNLP-AACL
    ImageTra: Real-Time Translation for Texts in Image and Video
    In 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: System Demonstrations, Dec 2025
  3. IJCNLP-AACL
    PRALEKHA: Cross-Lingual Document Alignment for Indic Languages
    Sanjay Suryanarayanan, Haiyue Song, Mohammed Safi Ur Rahman Khan, Anoop Kunchukuttan, and Raj Dabre
    In 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, acceptance rate 19% , Dec 2025
  4. IJCNLP-AACL
    Multilingual Iterative Model Pruning: What Matters?
    In 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, acceptance rate 19% , Dec 2025
  5. EMNLP
    CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation
    Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji, Vladimir Araujo, Israel Abebe Azime, and 27 more authors
    In Findings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025
  6. MT Summit
    bytF: How Good Are Byte Level N-Gram F-Scores for Automatic Machine Translation Evaluation?
    Raj Dabre, Hour Kaing, and Haiyue Song
    In Proceedings of Machine Translation Summit XX: Volume 1, Jun 2025
  7. COLING
    PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation
    In Proceedings of the 31st International Conference on Computational Linguistics, Jan 2025
  8. COLING
    Exploiting Word Sense Disambiguation in Large Language Models for Machine Translation
    In Proceedings of the First Workshop on Language Models for Low-Resource Languages, at COLING 2025 , Jan 2025
  9. COLING
    Connecting Ideas in ’Lower-Resource’ Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
    Aditya Joshi, Diptesh Kanojia, Heather Lent, Hour Kaing, and Haiyue Song
    In Tutorial at the 31st International Conference on Computational Linguistics (COLING 2025), 2025

2024

  1. NeurIPS
    CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
    David Romero, Chenyang Lyu, Haryo Akbarianto Wibowo, Santiago Góngora, Aishik Mandal, Sukannya Purkayastha, Jesús-Germán Ortiz-Barajas, Emilio Villa-Cueva, and 68 more authors
    In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024
  2. AMTA
    How Effective is Synthetic Data and Instruction Fine-tuning for Translation with Markup using LLMs?
    In Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), Sep 2024
  3. IWSLT
    iwslt.png
    NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task
    Raj Dabre and Haiyue Song
    In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), Aug 2024
  4. EAMT
    submerge.png
    SubMerge: Merging Equivalent Subword Tokenizations for Subword Regularized Models in Neural Machine Translation
    In Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), Jun 2024
  5. EAMT
    Linguistically Motivated Neural Machine Translation
    Haiyue Song, Hour Kaing, and Raj Dabre
    In Tutorial at the 25th Annual Conference of the European Association for Machine Translation (EAMT 2024), 2024
  6. KEMT
    Incorporating Hypernym Features for Improving Low-resource Neural Machine Translation
    Abhisek Chakrabarty, Haiyue Song, Raj Dabre, Hideki Tanaka, and Masao Utiyama
    In Proceedings of the First International Workshop on Knowledge-Enhanced Machine Translation, Jun 2024
  7. LREC-COLING
    nglueni.png
    NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages
    Francois Meyer, Haiyue Song, Abhisek Chakrabarty, Jan Buys, Raj Dabre, and Hideki Tanaka
    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024
  8. IWSDS
    Enhancing Personality Recognition in Dialogue by Data Augmentation and Heterogeneous Conversational Graph Networks
    Yahui Fu, Haiyue Song, Tianyu Zhao, and Tatsuya Kawahara
    In Proceedings of the 14th International Workshop on Spoken Dialogue Systems Technology (IWSDS 2024), 2024

2023

  1. EMNLP
    GPT-RE: In-context Learning for Relation Extraction using Large Language Models
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023
  2. ACL
    Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Jul 2023
  3. EAMT
    Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation
    In Proceedings of the 1st International Workshop on Multilingual, Multimodal and Multitask Language Generation (Multi3Generation) at EAMT 2023, 2023
  4. EACL
    Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
    In Findings of the Association for Computational Linguistics: EACL 2023, May 2023

2022

  1. AACL
    bertseg.png
    BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine Translation
    In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Nov 2022
  2. NAACL
    When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
    In Findings of the Association for Computational Linguistics: NAACL 2022, Jul 2022

2021

  1. ACL
    Video-guided Machine Translation with Spatial Hierarchical Attention Network
    Weiqi Gu, Haiyue Song, Chenhui Chu, and Sadao Kurohashi
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, Aug 2021

2020

  1. EMNLP
    A System for Worldwide COVID-19 Information Aggregation
    Akiko Aizawa, Frederic Bergeron, Junjie Chen, Fei Cheng, Katsuhiko Hayashi, Kentaro Inui, Hiroyoshi Ito, Daisuke Kawahara, and 21 more authors
    In Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020, also at the Workshop on NLP for COVID-19 at ACL 2020 , Dec 2020
  2. ACL
    Pre-training via Leveraging Assisting Languages for Neural Machine Translation
    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, Jul 2020
  3. LREC
    coursera.png
    Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
    In Proceedings of the 12th Language Resources and Evaluation Conference (LREC 2020), May 2020
  4. LREC
    JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
    Zhuoyuan Mao, Fabien Cromieres, Raj Dabre, Haiyue Song, and Sadao Kurohashi
    In Proceedings of the 12th Language Resources and Evaluation Conference (LREC 2020), May 2020

2018

  1. ICCAD
    iccad.png
    Invocation-driven Neural Approximate Computing with a Multiclass-Classifier and Multiple Approximators
    Haiyue Song, Chengwen Xu, Qiang Xu, Zhuoran Song, Naifeng Jing, Xiaoyao Liang, and Li Jiang
    In Proceedings of the International Conference on Computer-Aided Design (ICCAD 2018), Nov 2018
  2. FPGA
    A FPGA Friendly Approximate Computing Framework with Hybrid Neural Networks
    Haiyue Song, Xiang Song, Tianjian Li, Hao Dong, Naifeng Jing, Xiaoyao Liang, and Li Jiang
    In Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA 2018), abstract only , 2018

Domestic Conferences (non peer-reviewed)

2026

  1. NLP
    FormatRL: Format Reinforcement Learning for Structured Document Translation
    宋 海越, Johannes Eschbach-Dymanus, Hour Kaing, Sumire Honda, 田中 英輝, Bianka Buschbeck, and 内山 将夫
    In 言語処理学会第32回年次大会(NLP2026), Mar 2026
  2. NLP
    Profanity as a Cue: When LLMs Mistake Toxicity for Hate
    Haotian Ye, 宋 海越, Hour Kaing, 丁 塵辰, 田中 英輝, and 内山 将夫
    In 言語処理学会第32回年次大会(NLP2026), Mar 2026

2025

  1. YANS
    生成型自動評価指標のための最小ベイズリスク復号
    呂 博軒, 宋 海越, 上垣外 英剛, 田中 英輝, 内山 将夫, 船越 孝太郎, and 奥村 学
    In 第20回言語処理若手シンポジウム(YANS2025), 2025
  2. NLP
    Towards Scene Text Translation for Complex Writing Systems
    Hour Kaing, 宋 海越, 丁 塵辰, 毛 剣楠, 田中 英輝, and 内山 将夫
    In 言語処理学会第31回年次大会(NLP2025), Mar 2025

2024

  1. NLP
    Robust Neural Machine Translation for Abugidas by Glyph Perturbation
    In 言語処理学会第30回年次大会(NLP2024), Mar 2024

2023

  1. NLP
    Large Pre-trained Language Models with Multilingual Prompt for Japanese Natural Language Tasks
    In 言語処理学会第29回年次大会(NLP2023), Mar 2023

2022

  1. NLP
    Representative Data Selection for Sequence-to-Sequence Pre-training
    In 言語処理学会第28回年次大会(NLP2022), Mar 2022
  2. NLP
    Improving Medical Relation Extraction with Distantly Supervised Pre-training
    In 言語処理学会第28回年次大会(NLP2022), Mar 2022

2021

  1. NLP
    Self-supervised Dynamic Programming Encoding for Neural Machine Translation
    In 言語処理学会第27回年次大会(NLP2021), Mar 2021
  2. NLP
    Video-guided Machine Translation with Spatial Hierarchical Attention Network Encoder
    Weiqi Gu, Haiyue Song, Chenhui Chu, and Sadao Kurohashi
    In 言語処理学会第27回年次大会(NLP2021), Mar 2021

2020

  1. NLP
    Domain Adaptation of Neural Machine Translation through Multistage Fine-Tuning
    In 言語処理学会第26回年次大会(NLP2020), Mar 2020
  2. NLP
    ニューラル機械翻訳のための言語知識に基づくマルチタスク事前学習
    Zhuoyuan Mao, Raj Dabre, Fabien Cromieres, 宋 海越, 中尾 亮太, and 黒橋 禎夫
    In 言語処理学会第26回年次大会(NLP2020), Mar 2020

Grants

2025

  1. KAKENHI
    Improving Large Language Models for Low-Resource Languages with Diverse Writing Systems
    Haiyue Song
    2025
    Grant-in-Aid for Early-Career Scientists(若手研究), 2025 to 2026, KAKENHI 25K21290.

2021

  1. KAKENHI
    Multilingual Corpus Construction and Domain Adaptation for Low-Resource Machine Translation
    Haiyue Song
    2021
    JSPS Research Fellowship for Young Scientists (DC1), 2021 to 2023, KAKENHI 22KJ1724.

Other Presentations

2024

  1. Talk
    Presentation at CJNLP 2024
    Haiyue Song
    2024

2022

  1. Talk
    Presentation at the 14th Input Method Workshop (IM 2022)
    Haiyue Song
    2022
    第14回入力メソッドワークショップ
  2. Talk
    Presentation at the Kyoto University Symposium of the Department of Intelligence Science and Technology (AY2022)
    Haiyue Song
    2022
    2022年度 京都大学 情報学研究科 知能情報学専攻 シンポジウム
  3. Talk
    Lecture at 知能情報学演習, Kyoto University
    Haiyue Song
    2022