Coronavirus (Covid-19): Latest updates and information
Skip to main content Skip to navigation

Gabriele Pergola

Gabriele Pergola is a PhD student in Computer Science supervised by Prof. Yulan He.

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, opinion mining, topic extraction and clinical text mining.
More broadly, he is curious about the relationship between languages and information.

Reading groups

  • Organizer of the NLP Discussion Group at the University of Warwick, gathering students and researchers interested in Natural Language Processing. Email me if interested in joining the meetings.


  • CS918 Natural Language Processing - Lab Demonstrations and Seminars (Term I in 2018/2019 and 2019/2020).
  • CS909 Data Mining - Lab Demonstrations and Seminars (Term II in 2018/2019 and 2019/2020).


He holds a BSc and an MEng (cum laude) degree in Computer Engineering from the University of Palermo (Italy). Prior to joining Warwick, he received a Postgraduate Fellowship from the University of Rome "La Sapienza" (Italy) for designing and implementing machine learning systems to support the access to cultural heritage as part of the research project "Design and development of innovative technologies for the enjoyment of cultural heritage".


  • L. Gui, J. Leng, G. Pergola, Y. Zhou, R. Xu and Y. He. Neural Topic Model with Reinforcement Learning. in EMNLP-IJCNLP, Hong Kong, China, Nov. 2019.

        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 = "",
        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. TDAM: a Topic-Dependent Attention Model for Sentiment Analysis. Information Processing and Management, 56(6):102084, 2019.

            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 = {},
    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’ 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’ 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. Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context, The 2nd AAAI Workshop on Health Intelligence (AAAI18), New Orleans, Louisiana, USA, Feb. 2018.
  • , , , , . AI*IA, 294-307, .
  • , , . 339-346, CompSysTech, 
  • , , M., , , , , , , . AVI 


Lab Room CS2.33,
Computer Science Department,
University of Warwick,

gabriele dot pergola at warwick dot ac dot uk