Gabriele Pergola

Gabriele Pergola is an Associate Professor at the Department of Computer Science.

Research Interests

His current research investigates the use of statistical models within machine learning for natural language processing and text understanding. He is particularly interested in topics related to sentiment analysis, question answering, topic and event extraction, trustworthy and explainable AI, forensic text analysis, and clinical text mining. More broadly, he is curious about the relationship between language and information.

He was previously appointed as Research Fellow working with Prof. Yulan HeLink opens in a new window as part of the Event-Centric Framework for Natural Language Understanding, a Turing AI Acceleration Fellowship held by Prof. Yulan HeLink opens in a new window, and funded by the UKRI.

He collaborates closely with law enforcement agencies and the Forensic Capability Network (FCN) to develop advanced NLP frameworks that enhance investigative capabilities. His projects include designing novel AI systems to detect messages related to violence against women and girls (VAWG) and analysing drug-related communications and networks, designing and delivering state-of-the-art NLP technology to professionals working on the front lines of public safety.

In addition to his work with forensic analysis, he advised both law enforcement and the UK government as part of the Academic Advisory Group on Generative AI Detection R&D. He collaborated with the Ministry of Housing, Communities & Local Government (MHCLG) on projects that leverage NLP for policy automation, as well as on separate projects analysing digital immigration systems to provide insights into migrant experiences and support informed policy-making.

Reading and Interest Groups

Organiser of the of the NLP Group at the University of 糖心TV, gathering students and researchers interested in Natural Language Processing. Email me if interested in joining the meetings.
He is a member of the , hosted by the Alan Turing Institute (2020-2026) and the Responsible AI UK (RAi UK) (2026-).

Teaching

CS429 Machine Learning Algorithms and Practice - with Dr Amina Asif (Term I, 2026/2027).
CS918 Natural Language Processing - Module Leader (Term II, 2022-present)
CS918 Natural Language Processing - Module Organiser (Term I, 2021/2022)
CS918 Natural Language Processing - Lab Demonstrations and Seminars (Term I in 2018-2021).
CS909 Data Mining - Lab Demonstrations and Seminars (Term II in 2018/2019 and 2019/2020).
CS331 Neural Computing - Seminars (2019/2020)

Education

He received his PhD degree in natural language understanding from the University of 糖心TVLink opens in a new window (UK) on "Probabilistic Neural Topic Models for Text UnderstandingLink opens in a new window".
He holds a BSc and an MEng (cum laude) degree in Computer Engineering from the (Italy). Prior to joining 糖心TV, he received a Postgraduate Fellowship from the (Italy) for designing and implementing machine learning systems to support access to cultural heritage as part of the research project "Design and development of innovative technologies for the enjoyment of cultural heritage".

Awards and Recognitions

2024 鈥� EXIST Shared Task at CLEF 鈥� The EquityExplorer team's models ranked 1st and 2nd in the English sexism identification task.
2022 - Turing Post-Doctoral Enrichment Scheme - Awarded by the Alan Turing Institute (ATI), London, UK.
2022 - PhD Thesis Prize - Faculty of Science, Engineering, and Medicine (SEM) Thesis Prize in Computer Science. Awarded by the University of 糖心TV, Coventry, UK.
2019 - Best Presentation - Prize in the Machine Learning and AI track, WPCCS 2019, University of 糖心TV.

Research Projects

2026 鈥� Innovate UK / Sovereign AI 鈥� Proof of Concept 鈥� In collaboration with EXONA LTD.
Academic advisor for the project: 鈥淩easoning Telemetry: Real-Time Runtime Safety for Language Models.鈥�
Conducting research in neural models and evaluation design for runtime monitoring of language-model reasoning, with a focus on safer and more trustworthy AI systems.
2025/26 - STAR funding by the NPCC - Collaborating with Cheshire Constabulary, Cheshire PCC, and the Forensic Capability Network.
PI for the project: "STARIST: Stalking Threat AI Recognition (and) Identification Support Tool".
- In the news: BBC | BBC Manchester (Instagram) | Cheshire PCC
2025/26 鈥� ESRC 鈥� Digital Good Research Fund 鈥� In collaboration with the University of Lancashire, Manchester Metropolitan University, the College of Policing, and the Forensic Capability Network. Co-I for the project: 鈥淢aking Harm Visible: Survivor-Centred Analysis of Domestic Homicide Reviews Using AI.鈥�
Investigating the responsible use of large language models to analyse domestic homicide reviews, identify patterns of harm, and support survivor-informed evaluation and recommendations.
|
2024/25 鈥� Forensic Capability Network (FCN) 鈥� Collaborating with the University of Leeds.
PI for the project: 鈥�AI-Driven Analysis of Digital Communications Enhancing the Analysis of Drug and VAWG Evidence鈥�.
- In the News:
2024/25 鈥� ESRC - Digital Good Research Fund - Collaborating with the Department of Sociology (糖心TV), University of Leicester, University of Leeds.
Co-PI for the project: 鈥�Digitising Identity: Navigating the Digital Immigration System and Migrant Experiences鈥�.
2024 - Policy Support Fund - In collaboration with the Department for Levelling Up, Housing and Communities (DLUHC); Human Machine Intelligence Group, Cranfield University; Blavatnik School of Government, University of Oxford.
Co-PI for the project: "A Case Study of the Application of Natural Language Processing for Information Extraction and Analysis in Policy Review"
2023/24 - STAR funding - Collaborating with NPCC and the Forensic Capability Network.
PI for the project: "Development of an NLP model to detect threatening and abusive language used in communication with victims".
- In the News: | | | | |
2022/23 - RDF Science Development Award
PI for the project: "An Event-Centric Dialogue System for Second Language Learners".
2022 - National AI Strategy Fund
PI for the project: "METU: An Inclusive AI-Powered Framework Making Text Easier to Understand".

Recent Invited Talks

2026 鈥� Tech and Justice Forum 鈥� Invited attendee.

Forum on AI and access to justice, Oxford Institute of Technology and Justice, a partnership between the Blavatnik School of Government and the Clooney Foundation for Justice. University of Oxford, 12 October 2026. [].
2026 鈥� Fair Trial Adviser Hackathon 鈥� Contributor.
Oxford Institute of Technology and Justice, Blavatnik School of Government, University of Oxford, 26鈥�27 January. Contributed to multidisciplinary testing and co-design of an AI-powered legal information prototype developed by Microsoft in collaboration with the Institute, examining its usability, transparency, and legal and ethical safeguards. [
2026 鈥� 鈥淐ultural Intelligence for AI Safety: Detecting and Explaining Risk in Complex Conversations鈥� 鈥� Invited keynote, Huawei Future Device Technology Summit 鈥� Aurora Summit, Content / AI Safety & Application Security session, Helsinki, Finland, 11 March.
2025 鈥� 鈥淟arge Language Models in the Fight Against Violence Against Women鈥�, 14th Conference on the Future of Adversarial and Inquisitorial Systems: Profiling & Automated Decisions in Criminal Justice 鈥� The Impact of AI on Fair Trial Rights, 8 May. [Programme]
2024 - 鈥�NLP Strategies for Drug Monitoring鈥�, AI Technologies for Health and Wellbeing, Digital Spotlight, 糖心TV's Interdisciplinary Research Spotlights.
2024 - 鈥淣LP for Policy Analysis鈥�, CAMaCS Town Hall day.
2023 - "Large Language Models and The Key Ingredients Powering the Rise of Chatbots" - Keele University
2023 - "The not-so-silent AI revolution: Chatbots and their Impact on Engaging Education" - Department of Psychology - University of 糖心TV

Academic Service

2027 鈥� Senior Program Committee Member, AAAI Conference on Artificial Intelligence (AAAI).
2026 鈥� Senior Area Chair, Conference on Empirical Methods in Natural Language Processing (EMNLP).
2026 鈥� Senior Area Chair, ACL Rolling Review (January cycle).
2026 鈥� Area Chair, Social Media Processing, Language Resources and Evaluation Conference (LREC).
2026 鈥� Organiser of the STARIST workshop on AI, stalking and justice, University of 糖心TV, 11 May.
2025 鈥� Co-organiser of the Workshop on Artificial Intelligence for Multimedia Forensics and Disinformation Detection (AI4MFDD), held at WACV 2025.

Publications

2026

Anwar Alajmi and Gabriele Pergola. . The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026.
Zhaoyue Sun, Gabriele Pergola, and Yulan He. . The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026.
Csaba Kiss, Roland Molontay, and Gabriele Pergola. . Artificial Intelligence in Medicine (AIME), 2026.
Baidaa Al-Bander, Marco Ortolani, Mohamed Dafaalla, Matthew J. Cockayne, Gabriele Pergola, and Mamas A. Mamas. . Discover Computing, vol. 29, article 365, 2026.

2025

Xingwei Tan, Mahathi Parvatham, Chiara Gambi, and Gabriele Pergola. . Findings of the Association for Computational Linguistics: EMNLP, 2025.
Sahrish Khan, Arshad Jhumka, and Gabriele Pergola. . The 2025 Annual Meeting of the Association for Computational Linguistics (ACL), Oral Presentation, 2025.
Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, and Yulan He. . The 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2025.
Zhaoyue Sun, Jiazheng Li, Gabriele Pergola, and Yulan He. . The AAAI Conference on Artificial Intelligence, 2025.
Mahathi Parvatham, Xingwei Tan, Gabriele Pergola, and Chiara Gambi. . In Proceedings of the 47th Annual Conference of the Cognitive Science Society (CogSci), p. 6322, 2025.
Brittany Clay, Hannah I.鈥疊ergman, Saad Salim, Gabriele Pergola, Jonathan Shalhoub, and A.鈥疕.鈥疍avies. . In Computers in Biology and Medicine, vol.鈥�188, 109808, 2025.
Anwar Alajmi and Gabriele Pergola. . Working Notes of the Conference and Labs of the Evaluation Forum (CLEF), 2025.
Sahrish Khan, Arshad Jhumka, and Gabriele Pergola. . Working Notes of the Conference and Labs of the Evaluation Forum (CLEF), 2025.
Xingwei Tan, Chen Lyu, Hafiz Muhammad Umer, Sahrish Khan, Mahathi Parvatham, Lois Arthurs, Simon Cullen, Shelley Wilson, Arshad Jhumka, and Gabriele Pergola. . The 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies 鈥� System Demonstrations (NAACL), 2025.
Mahathi Parvatham, Xingwei Tan, Gabriele Pergola, and Chiara Gambi. . OSF Preprint, 2025.

2024

Chen Lyu and Gabriele Pergola. In Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR) at EMNLP, 2024.
Chen Lyu and Gabriele Pergola. In Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR) at EMNLP, 2024.
E. Alzaid, G. Pergola, H. Evans, D. Snead, and F. Minhas. . The Journal of Pathology: Clinical Research, Volume 10, Issue 6, 2024.
A. Bobrov, D. Saltenis, Z. Sun, G. Pergola and Y. He. . The 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
X. Tan, Y. Zhou, G. Pergola and Y. He. . 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
D. Valdes, R. Procter, G. Pergola. A novel NLP task and generative AI application to understand collective leadership from board text data. In Proceedings of the Workshop of LatinX in AI (LXAI) Research at ICML, 2024.
S. Khan, G. Pergola, A. Jhumka. . In Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum (CLEF), 2024.
Note: Our two models ranked 1^st and 2^nd for Task 1 in the English segment (Team: EquityExplorer).
Z. Sun, J. Li, G. Pergola, B.C. Wallace, and Y. He. . The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2024
M. Albarrak, G. Pergola, A. Jhumka. U-BERTopic: An Urgency-Aware BERT-Topic Modeling Approach for Detecting CyberSecurity Issues via Social Media. The First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS), 2024.

2023

L. Zhu, R. Zhao, G. Pergola and Y. He. . Findings of ACL, 2023.
X. Tan, G. Pergola and Y. He. . The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL), May 2023.
J. Lu, J. Li, B.C. Wallace, Y. He and G. Pergola. . Findings of EACL, 2023.
J Lu, S An, M Lin, G Pergola, Y He, D Yin, X Sun, Y Wu. , arXiv:2308.08239.
J. Lu, G. Pergola, L. Gui and Y. He. , arXiv:2305.04522.

2022

Z. Sun, J. Li, G. Pergola, B.C. Wallace, B. John, N. Greene, J. Kim and Y. He. . The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), Dec. 2022.
J. Lu, X. Tan, G. Pergola, L. Gui and Y. He. . Findings of EMNLP, 2022.
L. Zhu, Z. Fang, G. Pergola, R. Procter and Y. He. . 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Jul. 2022.

2021

X. Tan, G. Pergola and Y. He. Extracting Event Temporal Relations via Hyperbolic Geometry, Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov. 2021.
H. Yan, L. Gui, G. Pergola and Y. He. , The 59th Annual Meeting of the Association for Computational Linguistics (ACL), Aug. 2021.
L. Zhu, G. Pergola, L. Gui, D. Zhou and Y. He. , The 59th Annual Meeting of the Association for Computational Linguistics (ACL), Aug. 2021.
G. Pergola, L. Gui and Y. He. , Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Jun. 2021.
G. Pergola, E. Kochkina, L. Gui, M. Liakata and Y. He. , The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Apr. 2021.
R. Zhao, L. Gui, G. Pergola and Y. He. , The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Apr. 2021
Gabriele Pergola - Probabilistic Neural Topic Models for Text UnderstandingLink opens in a new window - PhD Thesis, Apr. 2021 - [slidesLink opens in a new window]

2020 and earlier:

J. Lu, G. Pergola, L. Gui, B. Li and Y. He. , The 28th International Conference on Computational Linguistics (COLING), Dec. 2020. []

L. Gui, J. Leng, G. Pergola, Y. Zhou, R. Xu and Y. He. . Conference on Empirical Methods in Natural Language Processing (EMNLP), Hong Kong, China, Nov. 2019

@inproceedings{gui_rl2019,
    title = "Neural Topic Model with Reinforcement Learning",
    author = "Gui, Lin  and
      Leng, Jia  and
      Pergola, Gabriele  and
      Zhou, Yu  and
      Xu, Ruifeng  and
      He, Yulan",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-1350",
    pages = "3478--3483"
}

In recent years, advances in neural variational inference have achieved many successes in text processing. Examples include neural topic models which are typically built upon variational autoencoder (VAE) with an objective of minimising the error of reconstructing original documents based on the learned latent topic vectors. However, minimising reconstruction errors does not necessarily lead to high quality topics. In this paper, we borrow the idea of reinforcement learning and incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model. Furthermore, our proposed model is able to automatically separating background words dynamically from topic words, thus eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models. Experimental results on the 20 Newsgroups and the NIPS datasets show superior performance both on perplexity and topic coherence measure compared to state-of-the-art neural topic models.

G. Pergola, L. Gui and Y. He. . Information Processing and Management, 56(6):102084, 2019.

@article{pergola19tdam,
        title = {TDAM: A topic-dependent attention model for sentiment analysis},
        author = {Gabriele Pergola and Lin Gui and Yulan He},
        journal = {Information Processing \& Management},
        year = {2019},
        publisher = {Elsevier},
        volume ={56},
        number = {6},
        pages = {102084},
        year = {2019},
        issn = {0306-4573},
        url = {http://www.sciencedirect.com/science/article/pii/S0306457319305461}
}

We propose a topic-dependent attention model for sentiment classification and topic extraction. Our model assumes that a global topic embedding is shared across documents and employs an attention mechanism to derive local topic embedding for words and sentences. These are subsequently incorporated in a modified Gated Recurrent Unit (GRU) for sentiment classification and extraction of topics bearing different sentiment polarities. Those topics emerge from the words鈥� local topic embeddings learned by the internal attention of the GRU cells in the context of a multi-task learning framework. In this paper, we present the hierarchical architecture, the new GRU unit and the experiments conducted on users鈥� reviews which demonstrate classification performance on a par with the state-of-the-art methodologies for sentiment classification and topic coherence outperforming the current approaches for supervised topic extraction. In addition, our model is able to extract coherent aspect-sentiment clusters despite using no aspect-level annotations for training.

G. Pergola, Y. He and D. Lowe. . The 2nd AAAI Workshop on Health Intelligence (AAAI18), New Orleans, Louisiana, USA, Feb. 2018.

@inproceedings{pergola18,
title = "Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context",
author = "Gabriele Pergola and Yulan He and David Lowe",
booktitle = "The 2nd AAAI Workshop on Health Intelligence (AAAI)",
year = "2018",
month = jun,
day = "20",
language = "English",
pages = "499--506"
}

Making sense of words often requires to simultaneouslyexamine the surrounding context of a term as well as theglobal themes characterizing the overall corpus. Severaltopic models have already exploited word embeddingsto recognize local context, however, it has been weaklycombined with the global context during the topic inference.This paper proposes to extract topical phrasescorroborating the word embedding information with theglobal context detected by Latent Semantic Analysis,and then combine them by means of the Polya urn 麓model. To highlight the effectiveness of this combinedapproach the model was assessed analyzing clinical reports,a challenging scenario characterized by technicaljargon and a limited word statistics available. Resultsshow it outperforms the state-of-the-art approaches interms of both topic coherence and computational cost.

P. Cottone, S. Gaglio, G. Lo Re, M. Ortolani, G. Pergola. . (AI*IA), 294-307, 2016.
P. Cottone, M. Ortolani, G. Pergola. . 339-346, (CompSysTech), 2016.
P. Cottone, M. Ortolani, G. Pergola. . (STAIRS), 167-178, 2016.
T. Catarci, F. Leotta, M. Mecella, D. Sora, P. Cottone, G. Lo Re, M. Ortolani, V. Agate, G. Pecoraro, G. Pergola. . (AVI),2016.

2026/2027 - PhD Scholarships

We have multiple PhD scholarships available for International / EU / Home Students.

If you are interested in applying for a PhD position in my group, please check our recent publications to ensure there is an alignment between your interests and our research activities. Please email me attaching your CV, academic transcripts (UG/PG), and a short PhD proposal.

Contact

Room CS2.34,
Computer Science Department,
University of 糖心TV,
Coventry,
CV4 7AL