Multimodal word meaning induction from minimal exposure to natural text

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Lazaridou, Angeliki
• dc.contributor.author Marelli, Marco
• dc.contributor.author Baroni, Marco
• dc.date.accessioned 2020-12-02T09:07:34Z
• dc.date.available 2020-12-02T09:07:34Z
• dc.date.issued 2017
• dc.description.abstract By the time they reach early adulthood, English speakers are familiar with the meaning of thousands of words. In the last decades, computational simulations known as distributional semantic models (DSMs) have demonstrated that it is possible to induce word meaning representations solely from word co‐occurrence statistics extracted from a large amount of text. However, while these models learn in batch mode from large corpora, human word learning proceeds incrementally after minimal exposure to new words. In this study, we run a set of experiments investigating whether minimal distributional evidence from very short passages suffices to trigger successful word learning in subjects, testing their linguistic and visual intuitions about the concepts associated with new words. After confirming that subjects are indeed very efficient distributional learners even from small amounts of evidence, we test a DSM on the same multimodal task, finding that it behaves in a remarkable human‐like way. We conclude that DSMs provide a convincing computational account of word learning even at the early stages in which a word is first encountered, and the way they build meaning representations can offer new insights into human language acquisition.en
• dc.description.sponsorship We thank the Cognitive Science editor and reviewers for constructive criticism. We also received useful feedback from the audience at *SEM 2015 and the International Meeting of the Psychonomic Society 2016. We acknowledge ERC 2011 Starting Independent Research Grant number 283554 (COMPOSES project). Marco Marelli conducted most of the work reported in this article while employed by the University of Trento. All authors equally contributed to the reported work.
• dc.format.mimetype application/pdf
• dc.identifier.citation Lazaridou A, Marelli M, Baroni M. Multimodal word meaning induction from minimal exposure to natural text. Cogn Sci. 2017 Mar 21;41(S4):677-705. DOI: 10.1111/cogs.12481
• dc.identifier.doi http://dx.doi.org/10.1111/cogs.12481
• dc.identifier.issn 0364-0213
• dc.identifier.uri http://hdl.handle.net/10230/45931
• dc.language.iso eng
• dc.publisher Wiley
• dc.relation.ispartof Cognitive Science. 2017 Mar 21;41(S4):677-705
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/283554
• dc.rights This is the peer reviewed version of the following article: Lazaridou A, Marelli M, Baroni M. Multimodal word meaning induction from minimal exposure to natural text. Cogn Sci. 2017 Mar 21;41(S4):677-705, which has been published in final form at http://dx.doi.org/10.1111/cogs.12481. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Word learning
• dc.subject.keyword Distributional semantics
• dc.subject.keyword Language and the visual world
• dc.subject.keyword One-shot learning
• dc.subject.keyword Multimodality
• dc.title Multimodal word meaning induction from minimal exposure to natural texten
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion