Exploiting social information in grounded language learning via grammatical reductions

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

4 Citations (Scopus)

Abstract

This paper uses an unsupervised model of grounded language acquisition to study the role that social cues play in language acquisition. The input to the model consists of (orthographically transcribed) child-directed utterances accompanied by the set of objects present in the non-linguistic context. Each object is annotated by social cues, indicating e.g., whether the caregiver is looking at or touching the object. We show how to model the task of inferring which objects are being talked about (and which words refer to which objects) as standard grammatical inference, and describe PCFG-based unigram models and adaptor grammar-based collocation models for the task. Exploiting social cues improves the performance of all models. Our models learn the relative importance of each social cue jointly with word-object mappings and collocation structure, consistent with the idea that children could discover the importance of particular social information sources during word learning.

Original languageEnglish
Title of host publicationProceedings of the 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics (ACL)
Pages883-891
Number of pages9
Volume1
ISBN (Print)9781937284244
Publication statusPublished - 2012
Event50th Annual Meeting of the Association for Computational Linguistics, ACL - 2012 - Jeju Island, Korea, Republic of
Duration: 8 Jul 201214 Jul 2012

Other

Other50th Annual Meeting of the Association for Computational Linguistics, ACL - 2012
CountryKorea, Republic of
CityJeju Island
Period8/07/1214/07/12

Cite this

Johnson, M., Demuth, K., & Frank, M. (2012). Exploiting social information in grounded language learning via grammatical reductions. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 (Vol. 1, pp. 883-891). Stroudsburg, PA: Association for Computational Linguistics (ACL).