Probabilistic Parsing for Spoken Language Applications

Stephanie Seneff


Abstract
A new natural language system, TINA, has been developed for applications involving spoken language tasks, which integrate key ideas from context free grammars, Augmented Transition Networks (ATN’s) [6], and Lexical Functional Grammars (LFG’s) [1]. The parser uses a best-first strategy, with probability assignments on all arcs obtained automatically from a set of example sentences. An initial context-free grammar, derived from the example sentences, is first converted to a probabilistic network structure. Control includes both top-down and bottom-up cycles, and key parameters are passed among nodes to deal with long-distance movement, agreement, and semantic constraints. The probabilities provide a natural mechanism for exploring more common grammatical constructions first. One novel feature of TINA is that it provides an atuomatic sentence generation capability, which has been very effective for identifying overgeneration problems. A fully integrated spoken language system using this parser is under development.
Anthology ID:
W89-0222
Volume:
Proceedings of the First International Workshop on Parsing Technologies
Month:
August
Year:
1989
Address:
Pittsburgh, Pennsylvania, USA
Venues:
IWPT | WS
SIG:
SIGPARSE
Publisher:
Carnegy Mellon University
Note:
Pages:
209–218
Language:
URL:
https://www.aclweb.org/anthology/W89-0222
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W89-0222.pdf