A bayesian framework for word segmentation: Exploring the effects of context

A bayesian framework for word segmentation: Exploring the effects of context (2009)

Cached

Download Links

by Sharon Goldwater , Thomas L. Griffiths , Mark Johnson

Venue:	In 46th Annual Meeting of the ACL
Citations:	26 - 7 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	A bayesian framework for word segmentation: Exploring the effects of context	INFERENCE
AUTHOR NAME	Sharon Goldwater	SVM HeaderParse 0.2
AUTHOR AFFIL	Preprint for publication in Cognition	SVM HeaderParse 0.2
AUTHOR NAME	Thomas L. Griffiths	SVM HeaderParse 0.2
AUTHOR AFFIL	Preprint for publication in Cognition	SVM HeaderParse 0.2
AUTHOR NAME	Mark Johnson	SVM HeaderParse 0.2
AUTHOR AFFIL	Preprint for publication in Cognition	SVM HeaderParse 0.2
ABSTRACT	Since the experiments of Saffran et al. (1996a), there has been a great deal of interest in the question of how statistical regularities in the speech stream might be used by infants to begin to identify individual words. In this work, we use computational modeling to explore the effects of different assumptions the learner might make regarding the nature of words – in particular, how these assumptions affect the kinds of words that are segmented from a corpus of transcribed child-directed speech. We develop several models within a Bayesian ideal observer framework, and use them to examine the consequences of assuming either that words are independent units, or units that help to predict other units. We show through empirical and theoretical results that the assumption of independence causes the learner to undersegment the corpus, with many two- and three-word sequences (e.g. what’s that, do you, in the house) misidentified as individual words. In contrast, when the learner assumes that words are predictive, the resulting segmentation is far more accurate. These results indicate that taking context into account is important for a statistical word segmentation strategy to be successful, and raise the possibility that even young infants may be able to exploit more subtle statistical patterns than have usually been considered. 1	SVM HeaderParse 0.2
YEAR	2009	INFERENCE
VENUE	In 46th Annual Meeting of the ACL	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	398--406	INFERENCE
CITATIONS	94 found	ParsCit 1.0