Unsupervised Dependency Parsing with Acoustic Cues release_7aaz5j4hjzhkhkxyzqe6hwnzbm

by John K Pate, Sharon Goldwater

Published in Transactions of the Association for Computational Linguistics by MIT Press - Journals.

2013   p63-74

Abstract

Unsupervised parsing is a difficult task that infants readily perform. Progress has been made on this task using text-based models, but few computational approaches have considered how infants might benefit from acoustic cues. This paper explores the hypothesis that word duration can help with learning syntax. We describe how duration information can be incorporated into an unsupervised Bayesian dependency parser whose only other source of information is the words themselves (without punctuation or parts of speech). Our results, evaluated on both adult-directed and child-directed utterances, show that using word duration can improve parse quality relative to words-only baselines. These results support the idea that acoustic cues provide useful evidence about syntactic structure for language-learning infants, and motivate the use of word duration cues in NLP tasks with speech.
In application/xml+jats format

Archived Files and Locations

application/pdf  268.9 kB
file_jyawjjhqdjekzbdy7ddpuqqnxm
www.aclweb.org (repository)
web.archive.org (webarchive)
application/pdf  419.5 kB
file_hsfasod67zfwpht5ndxmfywia4
www.research.ed.ac.uk (repository)
web.archive.org (webarchive)
application/pdf  257.6 kB
file_clhqm2gg6ne73g5mvm3rlefgnm
homepages.inf.ed.ac.uk (web)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Year   2013
Language   en ?
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  2307-387X
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: aca4d74e-acd0-4a4b-99c4-3d874efea8ad
API URL: JSON