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.

Multimodal word meaning induction from minimal exposure to natural text / Lazaridou, A.; Marelli, M.; Baroni, M.. - In: COGNITIVE SCIENCE. - ISSN 0364-0213. - 2017:4(2017), pp. 677-705. [10.1111/cogs.12481]

Multimodal word meaning induction from minimal exposure to natural text

A. Lazaridou;M. Marelli;M. Baroni
2017-01-01

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.
2017
4
Lazaridou, A.; Marelli, M.; Baroni, M.
Multimodal word meaning induction from minimal exposure to natural text / Lazaridou, A.; Marelli, M.; Baroni, M.. - In: COGNITIVE SCIENCE. - ISSN 0364-0213. - 2017:4(2017), pp. 677-705. [10.1111/cogs.12481]
File in questo prodotto:
File Dimensione Formato  
lazaridou-et-al-chimeras-cogsci.pdf

Solo gestori archivio

Descrizione: articolo
Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.57 MB
Formato Adobe PDF
3.57 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/193080
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 62
  • ???jsp.display-item.citation.isi??? 44
social impact