Email

michelebevila @ gmail . com

About me

Researcher in Natural Language Processing.

Machine Learning Scientist at Samaya AI.

Ex-FAIR (Facebook Artificial Intelligence Research), Meta’s fundamental research org. PhD alumnus of SapienzaNLP (supervisor prof. Roberto Navigli).

Trying to teach human language(s) to machines, one failure at a time. In my free time I like to pretend that I have free time.

Interested in: Natural Language Processing (NLP), Natural Language Generation, Information Retrieval, Lexical Semantics, Word Sense Disambiguation, Semantic Parsing

Publications

2023

  • Petroni F., Broscheit S., Piktus A., Lewis P., Izacard G., Hosseini L., Dwivedi-Yu J., Lomeli M., Schick T., Bevilacqua M., Mazaré P.E., Joulin A., Grave E., Riedel S. - Improving Wikipedia verifiability with AI, Nature Machine Intelligence, 2023. [paper]
  • Liu N.F., Lin K., Hewitt J., Paranjape A., Bevilacqua M., Petroni F., Liang P. - Lost in the Middle: How Language Models Use Long Contexts, TACL, 2023. [paper] [repo]
  • Srivastava A., Rastogi A., Rao A., et al. - Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models, TMLR, 2023. [paper] [repo]
  • Dessì R., Bevilacqua M., Gualdoni E., Rakotonirina N.C., Franzon F., Baroni M. - Cross-Domain Image Captioning with Discriminative Finetuning, Proceedings of CVPR, 2023. [paper]

2022

  • Bevilacqua M., Ottaviano G., Lewis P., Yi W., Riedel S., Petroni F., - Autoregressive Search Engines: Generating Substrings as Document Identifiers, arXiv, 2022. [paper] [repo]
  • Maru M., Conia S., Bevilacqua M., Navigli R. - Nibbling at the Hard Core of Word Sense Disambiguation, Proceedings of ACL, 2022. [paper] [repo+data]

2021

  • El Sheikh A., Bevilacqua M., Navigli R. - Integrating Personalized PageRank into Neural Word Sense Disambiguation, Proceedings of EMNLP, 2021 [paper][repo].
  • Blloshmi R., Bevilacqua B., Fabiano E., Caruso V., Navigli R. - SPRING Goes Online: End-to-End AMR Parsing and Generation, Proceedings of EMNLP (demo), 2021 [demo][paper].
  • Bevilacqua M., Pasini T., Raganato A., Navigli R. - Recent Trends in Word Sense Disambiguation: A Survey, Proceedings of IJCAI (survey), 2021 [paper].
  • Navigli R., Bevilacqua M., Conia S., Montagnini D., Cecconi F. - Ten Years of BabelNet: A Survey, Proceedings of IJCAI (survey), 2021 [paper].
  • Calabrese A., Bevilacqua M., Ross B., Tripodi R., Navigli R. - AAA: Fair Evaluation for Abuse Detection Systems Wanted, Proceedings of WebSci, 2021. [paper] [repo]
  • Bevilacqua M., Blloshmi M., Navigli R. - One SPRING to Rule Them Both:Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline, Proceedings of AAAI, 2021. [paper] [repo]

2020

  • Bevilacqua M., Maru M., Navigli R. - Generationary or: “How We Went beyond Sense Inventories and Learned to Gloss”, Proceedings of EMNLP, 2020. [paper] [website]
  • Calabrese A., Bevilacqua M., Navigli R. - EViLBERT: Learning Task-Agnostic Multimodal Sense Embeddings, Proceedings of IJCAI, 2020. [paper] [website]
  • Bevilacqua M., Navigli R. - Breaking Through the (80%) Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information, Proceedings of ACL (long paper), 2020. [paper] [repo]
  • Calabrese A., Bevilacqua M., Navigli R. - Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts, Proceedings of ACL (short paper), 2020. [paper] [website]
  • Lacerra C., Bevilacqua M., Pasini T., Navigli R. - CSI: A Coarse Sense Inventory for 85% Word Sense Disambiguation, Proceedings of AAAI, 2020. [paper] [website] [paper] [repo]

2019

  • Bevilacqua M., Navigli R. - Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation, Proceedings of RANLP (long paper), 2019. [paper] [repo]