I am an ICREA Research Professor in the Department of Translation and Language Sciences of the Universitat Pompeu Fabra (Barcelona, Spain), and the head of the Computational Linguistics and Linguistic Theory (COLT) research group.
My main research area is Computational Linguistics (aka Natural Language Processing). I am interested in how humans convey meaning through language. I work with computational models (distributional semantics, neural networks) that are able to induce very rich and flexible linguistic representations directly from examples of how people use language. I am currently working on reference, or how we use language to talk about the world: I just need to utter a bunch of words, for instance "the smart woman we met the other day at the meeting", and my interlocutor will be able to identify the person I mean. I am building computational models that are able to do this, like humans do. I am funded by an ERC Starting Grant.
representative publications
- Boleda, G. 2020. Distributional Semantics and Linguistic Theory. Annual Review of Linguistics, Vol. 6: 213-23. [Pre-print version]
- McNally, L., G. Boleda. 2017. Conceptual Versus Referential Affordance in Concept Composition. In Yoad Winter & James Hampton (eds.) Compositionality and Concepts in Linguistics and Psychology 245-267. Springer.
- Aina, L., Silberer, C., Sorodoc, I., Westera, M., Boleda, G. 2019. What do entity-centric models learn? Insights from entity linking in multi-party dialogue. In Proceedings of NAACL-HLT 2019, 3772-3783.
news
- July 2020: Area Chair for Lexical Semantics at EACL 2020.
- June 2020: Invited online talk at Potsdam Computational Linguistics Colloquium, Potsdam, Germany: "Language and use: interaction between referential context and lexicon".
- May 2020: Co-organizing the GeCKo symposium on Integrating Generic and Contextual Kowledge, online, May 18.
- May 2020: Two posters accepted at CogSci 2020: Modeling word interpretation with deep language models: The interaction between expectations and lexical information (Aina, Brochhagen, Boleda) and Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks (Gulordava, Brochhagen, Boleda).
- April 2020: Invited online talk at CLASP Seminar, Gothenburg, Sweden: "Distributional Semantics and Linguistic Theory".
- April 2020: Paper accepted at ACL 2020: Probing for referential information in language models, with Ionut-Teodor Sorodoc and Kristina Gulordava.
- March 2020: Invited online talk at LingLunch Paris Diderot, Department of Linguistics, Université Paris Diderot, Paris, France: "Distributional Semantics and Linguistic Theory".
- February 2020: Paper accepted at LREC 2020: Object Naming in Language and Vision: A Survey and a New Dataset, with Carina Silberer and Sina Zarrieß.
- January 2020: Annual Review of Linguistics paper out! Distributional Semantics and Linguistic Theory (Vol. 6: 213-23).
- December 2019: Talk at DLBCN 2019 on joint work with Marco Del Tredici and Raquel Fernandez, published at NAACL: Short-term meaning shift: a distributional exploration.
- December 2019: Very happy to start my job as an ICREA Research Professor. A great honor and a long-standing dream!
- October 2019: Will be an invited speaker at the LANTERN 2020 workshop (Barcelona, September 2020).
- October 2019: Invited speaker at EurNLP, London, UK, October 11.
- October 2019: Keynote speaker at 15th KONVENS, Erlangen, Germany, October 9-11.
- August 2019: Participated in the Lorentz Center workshop on Compositionality in Brains and Machines, Leiden, The Netherlands, August 5-9 2019.
- August 2019: Short paper presented at ACL 2019: Putting words in context: LSTM language models and lexical ambiguity, with Laura Aina and Kristina Gulordava.