Modelling function words improves unsupervised word segmentation

Mark Johnson, Anne Christophe, Katherine Demuth, Emmanuel Dupoux

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

9 Citations (Scopus)

Abstract

Inspired by experimental psychological findings suggesting that function words play a special role in word learning, we make a simple modification to an Adaptor Grammar based Bayesian word segmentation model to allow it to learn sequences of monosyllabic "function words" at the beginnings and endings of collocations of (possibly multi-syllabic) words. This modification improves unsupervised word segmentation on the standard Bernstein- Ratner (1987) corpus of child-directed English by more than 4% token f-score compared to a model identical except that it does not special-case "function words", setting a new state-of-the-art of 92.4% token f-score. Our function word model assumes that function words appear at the left periphery, and while this is true of languages such as English, it is not true universally. We show that a learner can use Bayesian model selection to determine the location of function words in their language, even though the input to the model only consists of unsegmented sequences of phones. Thus our computational models support the hypothesis that function words play a special role in word learning.

Original languageEnglish
Title of host publicationLong Papers
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics (ACL)
Pages282-292
Number of pages11
Volume1
ISBN (Print)9781937284725
Publication statusPublished - 2014
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: 22 Jun 201427 Jun 2014

Other

Other52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
CountryUnited States
CityBaltimore, MD
Period22/06/1427/06/14

Fingerprint Dive into the research topics of 'Modelling function words improves unsupervised word segmentation'. Together they form a unique fingerprint.

  • Cite this

    Johnson, M., Christophe, A., Demuth, K., & Dupoux, E. (2014). Modelling function words improves unsupervised word segmentation. In Long Papers (Vol. 1, pp. 282-292). Stroudsburg, PA: Association for Computational Linguistics (ACL).