Marco Baroni

Marco Baroni

Universitat Pompeu Fabra

Social & Behavioural Sciences

Marco Baroni received a PhD in Linguistics from the University of California, Los Angeles, in the year 2000. After several experiences in research and industry, he joined the Center for Mind/Brain Sciences of the University of Trento, where he became associate professor in 2013. In 2016, Marco joined the Facebook Artificial Intelligence Research team. In 2019, he became ICREA research professor, affiliated with the Linguistics Department of Pompeu Fabra University in Barcelona. Marco's work in the areas of multimodal and compositional distributed semantics has received widespread recognition, including a Google Research Award, an ERC Starting Grant, and the ICAI-JAIR best paper prize and the ACL test of time award. Marco's current research focuses on a better understanding of artificial neural networks, focusing in particular on what they can teach us about human language acquisition and processing.

Research interests

Marco is interested in human language and how it is acquired. To gain insights into these questions, he develops and studies computational systems, in particular deep neural networks, that acquire aspects of language from realistic input data. By analyzing the inner dynamics and external behaviour of these systems, we can gain insights into questions such as: how much linguistic knowledge is already implicitly present in input distributions, what are the minimal priors necessary for learning, what is the space of solutions to the communication challenges that led to the evolution of language, and so on. The ultimate goal of Marco’s research is to bring about a more precise characterization of what is unique about the human language faculty.

Selected publications

– Kharitonov E & Baroni M 2020. Emergent Language Generalization and Acquisition Speed are not tied to Compositionality. Proceedings of the EMNLP 2020 Workshop on Analyzing and Interpreting Neural Networks for NLP (Blackbox NLP), EastStroudsburg PA: ACL.

– Ruis L, Andreas J, Baroni M, Bouchacourt D & Lake B 2020, A benchmark for systematic generalization in grounded language understanding. Proceedings of NeurIPS 2020 (34th Conference on Neural Information Processing Systems): Curran Asoociates.

Baroni M 2020, ‘Linguistic generalization and compositionality in modern artificial neural networks’, Philosophical Transactions Of The Royal Society B-biological Sciences, 375, 1791, 20190307.

– Chaabouni R, Kharitonov E, Bouchacourt D, Dupoux E & Baroni M 2020. ‘Compositionality and Generalization in Emergent Languages’. Proceedings of ACL (The 58th annual meeting of the Association for Computational Linguistics), 4427 – 4442.

– Kharitonov E, Chaabouni R, Bouchacourt D & Baroni M 2020, ‘Entropy Minimization In Emergent Languages’. ICML 2020 (International Conference on Machine Learning).

Selected research activities

I was awarded the ACL 10-year test of time award, assigned to an especially influential paper published in any Association-of-Computational-Linguistics-sponsored venue, for “Distributional Memory: A General Framework for Corpus-Based Semantics” (co-authored with A. Lenci, Computational Linguistics 2010). I was also author of the award runner-up, “Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space” (co-authored with R. Zamparelli, Proceedings of EMNLP 2010).

I was invited to give a lecture at the MILA/CIFAR summer school on Deep Learning and Reinforcement learning (the most prestigious school in the area), as well as at the MIT Center for Brains, Minds and Machines.

Besides my usual role as editor of the Transactions of the Association for Computational Linguistics, I acted as area chair for the ACL conference.