PCFGs with syntactic and prosodic indicators of speech repairs

Authors:
John Hale;Izhak Shafran;Lisa Yung;Bonnie Dorr;Mary Harper;Anna Krasnyanskaya;Matthew Lease;Yang Liu;Brian Roark;Matthew Snover;Robin Stewart
Affiliations:
Michigan State University;Johns Hopkins University/;Johns Hopkins University/;University of Maryland, College Park;University of Maryland, College Park and Purdue University;UCLA;Brown University;University of Texas at Dallas;Oregon Health & Sciences University;University of Maryland, College Park;Williams College
Venue:
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Year:
2006

Citing 15
Cited 5

Bagging predictors

Machine Learning
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
Speech repairs, intonational phrases, and discourse markers: modeling speakers' utterances in spoken dialogue

Computational Linguistics
Robust garden path parsing

Natural Language Engineering
A maximum-entropy-inspired parser

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Meta-rules as a basis for processing ill-formed input

Computational Linguistics - Special issue on ill-formed input
Deterministic parsing of syntactic non-fluencies

ACL '83 Proceedings of the 21st annual meeting on Association for Computational Linguistics
A syntactic framework for speech repairs and other disruptions

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Edit detection and parsing for transcribed speech

NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
The Penn Treebank: annotating predicate argument structure

HLT '94 Proceedings of the workshop on Human Language Technology
Structural event detection for rich transcription of speech

Structural event detection for rich transcription of speech
A TAG-based noisy channel model of speech repairs

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Effective use of prosody in parsing conversational speech

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Statistical language modeling for speech disfluencies

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Exploring features for identifying edited regions in disfluent sentences

Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology

A unified syntactic model for parsing fluent and disfluent speech

HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
A syntactic time-series model for parsing fluent and disfluent speech

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Improved syntactic models for parsing speech with repairs

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Parsing speech repair without specialized grammar symbols

ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Word buffering models for improved speech repair parsing

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

A grammatical method of combining two kinds of speech repair cues is presented. One cue, prosodic disjuncture, is detected by a decision tree-based ensemble classifier that uses acoustic cues to identify where normal prosody seems to be interrupted (Lickley, 1996). The other cue, syntactic parallelism, codifies the expectation that repairs continue a syntactic category that was left unfinished in the reparandum (Levelt, 1983). The two cues are combined in a Treebank PCFG whose states are split using a few simple tree transformations. Parsing performance on the Switchboard and Fisher corpora suggests that these two cues help to locate speech repairs in a synergistic way.