About me

Hi👋, I am Yi-Ling.

I am a research associate at The Alan Turing Institute, working on online safety and potential interventions.

My work currently addresses online harms through abuse detection, response generation and model evaluation. I am passionate about developing applications for positive impacts and societal issues in the real world (e.g. misinformation, abuse, and violence), understanding the social impact of AI systems, as well as making AI safer and more reliable. I am also interested in research areas such as multilinguality, generalisable natural language processing, LLM hallucination mitigation, argument mining and generation, and psychology. I completed my PhD in Information Engineering and Computer Science at the University of Trento and Fondazione Bruno Kessler, where I was advised by Marco Guerini.


  • May 2024: Two papers accepted at NAACL 2024! I am also co-organising The 8th Workshop on Online Abuse and Harms (WOAH) on 20 June 2024 at NAACL.
  • November 2023: I gave a talk on NLP for Online Harm Mitigation at the University of Jaén on November 8 2023.
  • October 2023: I was on a panel discussing The Challenge of Disinformation in Generative AI at Symposium on AI, Free Speech and Human Rights on 13 October 2023 in Nashville, Tennessee.
  • October 2023: I gave a talk on Language Models for Online Safety at Ofcom Online Safety Research Workshop on 9 October 2023 in London.
  • April 2023: I am co-organising The 1st Workshop on Counter Speech for Online Abuse on 11 September 2023 at SigdialxINLG 2023 in Prague!
  • March 2023: I was on a panel discussing the realities of online harm in the UK and countermeassures to it using AI at AI UK 2023
  • January 2023: I am co-organising The 7th Workshop on Online Abuse and Harms (WOAH) on 13 July 2023 at ACL in Toronto, Canada!
  • November 2022: I gave a talk at Heriot-Watt University about automatic hate countering using counter speech on 9 November 2022.
  • April 2022: I successfully defended my PhD thesis 🥳🎉✨🌈
  • September 2021: Our work on counter narrative classification has been accepted at ArgMining 2021!
  • June 2021: Our paper on knowledge-bound counter narrative generation has been accepted at ACL Findings and NLP4PI!
  • May 2021: Our work on hate monitoring/countering platform has been accepted at the journal Online Social Networks and Media!
  • January-April 2021: Interned at HiTZ Center - Ixa Group with Rodrigo Agerri

Selected Publications

  • Yi-Ling Chung and Jonathan Bright. On the Effectiveness of Adversarial Robustness for Abuse Mitigation with Counterspeech. NAACL 2024 (Long Paper) [Dataset & Code]
  • Helena Bonaldi, Yi-Ling Chung, Gavin Abercrombie, Marco Guerini. NLP for Counterspeech against Hate: A Survey and How-To Guide. NAACL Findings 2024 (Long Paper) [arXiv]
  • Yi-Ling Chung, Gavin Abercrombie, Florence Enock, Jonathan Bright, Verena Rieser. Understanding Counterspeech for Online Harm Mitigation. 2023 [arXiv]
  • Yi-Ling Chung, Marco Guerini, and Rodrigo Agerri. Multilingual Counter Narrative Type Classification. Workshop on Argument Mining 2021 [Paper]
  • Yi-Ling Chung, Serra Sinem Tekiroğlu, and Marco Guerini. Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech. ACL Findings 2021 (Long Paper) Also accepted at NLP for Positive Impact workshop 2021 [Paper] [Slides] [Dataset] [Code]
  • Yi-Ling Chung, Serra Sinem Tekiroğlu, Sara Tonelli, and Marco Guerini. Empowering NGOs in Countering Online Hate Messages. Online Social Networks and Media (OSNM), 24 (2021): 100150 [Paper][arXiv]
  • Yi-Ling Chung, Serra Sinem Tekiroğlu, and Marco Guerini. Italian Counter Narrative Generation to Fight Online Hate Speech. In the Seventh Italian Conference on Computational Linguistics Clic-it 2020 [Paper] [video]
  • Serra Sinem Tekiroğlu, Yi-Ling Chung, and Marco Guerini. Generating Counter Narratives against Online Hate Speech: Data and Strategies. ACL 2020 (Long Paper) [Paper]
  • Yi-Ling Chung, Elizaveta Kuzmenko, Serra Sinem Tekiroğlu and Marco Guerini. CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate. ACL 2019 (Long Paper) [Paper] [Dataset]
  • Rodrigo Agerri, Yiling Chung, Itziar Aldabe, Nora Aranberri, Gorka Labaka and German Rigau. Building Named Entity Recognition Taggers via Parallel Corpora. LREC 2018 [Paper]

  • PhD Thesis: Counter Narrative Generation for Fighting Online Hate Speech. University of Trento, Italy. 2022.


  • PhD, Computer Science, University of Trento/Fondazione Bruno Kessler
  • MSc in European Masters in Language and Communication Technologies
  • MSc in Cognitive Science, National Cheng Kung University, Taiwan
  • BSc in Psychology, Kaohsiung Medical University, Taiwan

Work Experience

  • Research Associate, The Alan Turing Institute (January 2022-present)
  • NLP internship, Vicomtech, Basque country (January-August 2017)
  • Researcher at Department of Psychological and Educational Testing, National Taiwan Normal University, Taiwan (March-July 2015)


  • Served as a reviewer for LREC, ACL, NeurIPS, EMNLP, WOAH, COLING, Clic-it
  • ACL 2019 Student Volunteer
  • AthNLP Summer School Scholarship 2019
  • Taiwanese European Scholarship for European Masters in Language and Communication Technologies

Fun Facts

  • I enjoy spending time in the kitchen trying delicious/creative meals 🍱🥟🥗
  • I also love exploring the beauty of nature 🏞️⛩️🌈🌊
  • My New Year resolution is to learn to play guitar and pick up my rusty piano skill 🧐😎🤔