Unsupervised Dependency Parsing with Acoustic Cues

John K Pate, Sharon Goldwater


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.
Anthology ID:
Q13-1006
Volume:
Transactions of the Association for Computational Linguistics, Volume 1
Month:
Year:
2013
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
63–74
Language:
URL:
https://aclanthology.org/Q13-1006
DOI:
10.1162/tacl_a_00210
Bibkey:
Cite (ACL):
John K Pate and Sharon Goldwater. 2013. Unsupervised Dependency Parsing with Acoustic Cues. Transactions of the Association for Computational Linguistics, 1:63–74.
Cite (Informal):
Unsupervised Dependency Parsing with Acoustic Cues (Pate & Goldwater, TACL 2013)
Copy Citation:
PDF:
https://aclanthology.org/Q13-1006.pdf
Video:
 https://aclanthology.org/Q13-1006.mp4