Huiyuan Lai (赖辉源)

University of Groningen
Office: Harmonie Complex, Room 1311.417, 9712 EK Groningen, The Netherlands
Email: huiyuanlai dot l AT gmail.com


NEWS PUBLICATIONS ABOUT

* denotes equal contribution.

2024

  • mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models.
    HuiyuanLai and Malvina Nissim.
    In Proceedings of ACL 2024.
    [bib] [pdf] [code]
  • Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models.
    Daniela Occhipinti, Michele Marchi, Irene Mondella, HuiyuanLai, Felice Dell'Orletta, Malvina Nissim, and Marco Guerini.
    In Proceedings of ACL 2024 Findings.
    [bib] [pdf] [code]
  • A Survey on Automatic Generation of Figurative Language: From Rule-based Systems to Large Language Models.
    HuiyuanLai and Malvina Nissim.
    ACM Computing Surveys.
    [bib] [pdf] [data]
  • Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation.
    Esther Ploeger, Huiyuan Lai, Rik van Noord, Antonio Toral.
    In Proceedings of the 25th Annual Conference of The European Association for Machine Translation.
    [bib] [pdf]
  • ReproHum #0033-3: Comparable Relative Results with Lower Absolute Values in a Reproduction Study.
    Yiru Li, HuiyuanLai, Antonio Toral and Malvina Nissim.
    In Proceedings of the 4th Workshop on Human Evaluation of NLP Systems.
    [bib] [pdf]
  • ReproHum #0892-01: The painful route to consistent results: A reproduction study of human evaluation in NLG.
    Irene Mondella, HuiyuanLai and Malvina Nissim.
    In Proceedings of the 4th Workshop on Human Evaluation of NLP Systems.
    [bib] [pdf]
  • Neural Text Rewriting: Style Transfer, Figurative Language, and Beyond.
    HuiyuanLai.
    PhD Thesis; University of Groningen.
    [bib] [pdf]

2023

  • Multidimensional Evaluation for Text Style Transfer Using ChatGPT.
    HuiyuanLai, Antonio Toral and Malvina Nissim.
    Arxiv preprint.
    [bib] [pdf] [code]
  • Giving Dutch Some Style: Data and Models for Text Formality Transfer in Dutch.
    Marieke Weultjes, HuiyuanLai, Malvina Nissim.
    In Proceedings of the 33rd Meeting of Computational Linguistics in The Netherlands (Abstract Submission).
    [bib] [pdf]
  • Same Trends, Different Answers: Insights from a Replication Study of Human Plausibility Judgments on Narrative Continuations.
    Yiru Li, HuiyuanLai, Antonio Toral and Malvina Nissim.
    In Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems (@ RANLP 2023).
    [bib] [pdf]
  • Multilingual Multi-Figurative Language Detection.
    HuiyuanLai, Antonio Toral and Malvina Nissim.
    In Proceedings of ACL 2023 Findings.
    [bib] [pdf] [code]
  • Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation.
    Chunliu Wang*, HuiyuanLai*, Malvina Nissim and Johan Bos.
    In Proceedings of ACL 2023 Findings.
    [bib] [pdf] [code]
  • Responsibility Perspective Transfer for Italian Femicide News.
    Gosse Minnema*, HuiyuanLai*, Benedetta Muscato and Malvina Nissim.
    In Proceedings of ACL 2023 Findings.
    [bib] [pdf] [code]
  • Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP.
    Anya Belz, Craig Thomson, Ehud Reiter, et al.
    In Proceedings of the Fourth Workshop on Insights from Negative Results in NLP (@ EACL 2023).
    [bib] [pdf]
  • A Text Style Transfer System for Reducing the Physician-Patient Expertise Gap: an Analysis with Automatic and Human Evaluations.
    Luca Bacco, Felice Dell'Orletta, HuiyuanLai, Mario Merone, Malvina Nissim
    Expert Systems with Applications.
    [bib] [pdf]

2022

  • Multi-Figurative Language Generation.
    HuiyuanLai and Malvina Nissim.
    In Proceedings of COLING 2022.
    [bib] [pdf] [code] [slides]
  • Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer.
    HuiyuanLai, Jiali Mao, Antonio Toral and Malvina Nissim.
    In Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (@ ACL 2022).
    [bib] [pdf] [code] [slides]
  • Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer.
    HuiyuanLai, Antonio Toral and Malvina Nissim.
    In Proceedings of ACL 2022.
    [bib] [pdf] [code] [slides]

2021

  • Generic resources are what you need: Style transfer tasks without task-specific parallel training data.
    HuiyuanLai, Antonio Toral and Malvina Nissim.
    In Proceedings of EMNLP 2021.
    [bib] [pdf] [code] [slides]
  • Human Perception in Natural Language Generation.
    Lorenzo De Mattei*, HuiyuanLai*, Felice Dell’Orletta, Malvina Nissim.
    In Proceedings of the 1st Workshop on Generation Evaluation and Metrics (@ ACL 2021).
    [bib] [pdf]
  • Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer.
    HuiyuanLai, Antonio Toral and Malvina Nissim.
    In Proceedings of ACL 2021.
    [bib] [pdf] [code] [slides]

2020

  • On the interaction of automatic evaluation and task framing in headline style transfer.
    Lorenzo De Mattei, Michele Cafagna, HuiyuanLai, Felice Dell’Orletta, Malvina Nissim and Albert Gatt.
    In Proceedings of the 1st Workshop on Evaluating NLG Evaluation (@ INLG 2020).
    [bib] [pdf]
  • Bi-Directional Attention Comparison for Semantic Sentence Matching.
    HuiyuanLai, Yizheng Tao, Chunliu Wang, Lunfan Xu, Dingyong Tang, Gongliang Li.
    Multimedia Tools and Applications, 2019.
    [bib] [pdf]

2019

  • 文本相似度计算方法研究综述 (A Review of Text Similarity Approaches).
    王春柳, 杨永辉, 邓霏, 赖辉源.
    情报科学, 2019.
    [bib] [pdf]

© Huiyuan Lai | Last updated: June 2024