Advanced search
1 file | 13.42 MB Add to list

Multimodal word meaning induction from minimal exposure to natural text

(2017) COGNITIVE SCIENCE. 41. p.677-705
Author
Organization
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.

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 13.42 MB

Citation

Please use this url to cite or link to this publication:

MLA
Lazaridou, Angeliki, Marco Marelli, and Marco Baroni. “Multimodal Word Meaning Induction from Minimal Exposure to Natural Text.” COGNITIVE SCIENCE 41 (2017): 677–705. Print.
APA
Lazaridou, A., Marelli, M., & Baroni, M. (2017). Multimodal word meaning induction from minimal exposure to natural text. COGNITIVE SCIENCE, 41, 677–705.
Chicago author-date
Lazaridou, Angeliki, Marco Marelli, and Marco Baroni. 2017. “Multimodal Word Meaning Induction from Minimal Exposure to Natural Text.” Cognitive Science 41: 677–705.
Chicago author-date (all authors)
Lazaridou, Angeliki, Marco Marelli, and Marco Baroni. 2017. “Multimodal Word Meaning Induction from Minimal Exposure to Natural Text.” Cognitive Science 41: 677–705.
Vancouver
1.
Lazaridou A, Marelli M, Baroni M. Multimodal word meaning induction from minimal exposure to natural text. COGNITIVE SCIENCE. Wiley-Blackwell; 2017;41:677–705.
IEEE
[1]
A. Lazaridou, M. Marelli, and M. Baroni, “Multimodal word meaning induction from minimal exposure to natural text,” COGNITIVE SCIENCE, vol. 41, pp. 677–705, 2017.
@article{8552600,
  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.},
  author       = {Lazaridou, Angeliki and Marelli, Marco and Baroni, Marco},
  issn         = {0364-0213},
  journal      = {COGNITIVE SCIENCE},
  language     = {eng},
  pages        = {677--705},
  publisher    = {Wiley-Blackwell},
  title        = {Multimodal word meaning induction from minimal exposure to natural text},
  url          = {http://dx.doi.org/10.1111/cogs.12481},
  volume       = {41},
  year         = {2017},
}

Altmetric
View in Altmetric
Web of Science
Times cited: