Linguistic generalization and compositionality in modern artificial neural networks.

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Baroni, Marco
• dc.date.accessioned 2020-01-31T12:20:23Z
• dc.date.available 2020-01-31T12:20:23Z
• dc.date.issued 2020
• dc.description.abstract In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess e ective generalization abilities. It is widely assumed that humans handle linguistic productivity by means of algebraic compositional rules: Are deep networks similarly compositional? After reviewing the main innovations characterizing current deep language processing networks, I discuss a set of studies suggesting that deep networks are capable of subtle grammar-dependent generalizations, but also that they do not rely on systematic compositional rules. I argue that the intriguing behaviour of these devices (still awaiting a full understanding) should be of interest to linguists and cognitive scientists, as it o ers a new perspective on possible computational strategies to deal with linguistic productivity beyond rule-based compositionality, and it might lead to new insights into the less systematic generalization patterns that also appear in natural language.
• dc.format.mimetype application/pdf
• dc.identifier.citation Baroni M. Linguistic generalization and compositionality in modern artificial neural networks. Philos Trans R Soc Lond B Biol Sci. 2020 Feb 3; 375(1791). DOI: 10.1098/rstb.2019.0307
• dc.identifier.doi http://dx.doi.org/10.1098/rstb.2019.0307
• dc.identifier.issn 0962-8436
• dc.identifier.uri http://hdl.handle.net/10230/43459
• dc.language.iso eng
• dc.publisher Royal Society
• dc.relation.ispartof Philos Trans R Soc Lond B Biol Sci. 2020 Feb 3; 375(1791). DOI: 10.1098/rstb.2019.0307
• dc.rights © The Royal Society https://doi.org/10.1098/rstb.2019.0307
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Artificial neural networks
• dc.subject.keyword Deep learning
• dc.subject.keyword Linguistic productivity
• dc.subject.keyword Compositionality
• dc.title Linguistic generalization and compositionality in modern artificial neural networks.
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion