TFlex: speeding up deep parsing with strategic pruning

Authors:
Myroslava O. Dzikovska;Carolyn P. Rose
Affiliations:
University of Edinburgh, Edinburgh, UK;Carnegie Mellon University, Pittsburgh, PA
Venue:
Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology
Year:
2005

Citing 3
Cited 1

A practical semantic representation for natural language parsing

A practical semantic representation for natural language parsing
Skeletons in the parser: using a shallow parser to improve deep parsing

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Discourse annotation in the Monroe corpus

DiscAnnotation '04 Proceedings of the 2004 ACL Workshop on Discourse Annotation

Chester: towards a personal medication advisor

Journal of Biomedical Informatics - Special issue: Dialog systems for health communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method for speeding up a deep parser through backbone extraction and pruning based on CFG ambiguity packing. The TRIPS grammar is a wide-coverage grammar for deep natural language understanding in dialogue, utilized in 6 different application domains, and with high coverage and sentence-level accuracy on human-human task-oriented dialogue corpora (Dzikovska, 2004). The TRIPS parser uses a best-first beam search algorithm and a chart size limit, both of which are a form of pruning focused on finding an n-best list of interpretations. However, for longer sentences limiting the chart size results in failed parses, while increasing the chart size limits significantly impacts the parsing speed.