Second International Conference on Spoken Language Processing (ICSLP'92)

Banff, Alberta, Canada
October 13-16, 1992

PARSEC: A Constraint-based Framework for Spoken Language Understanding

Carla B. Zoltowski, Mary P. Harper, Leah H. Jamieson, Randall A. Helzerman

School of Electrical Engineering, Purdue University, West Lafayette, IN, USA

We have extended Maruyama's [5, 6, 7] constraint dependency grammar (CDG) to process a lattice or graph of sentence hypotheses instead of separate text strings. A post-processor to a speech recognizer producing N-best hypotheses generates the word graph representation, which is then augmented with information required for parsing. We will summarize the CDG parsing algorithm and then describe how the algorithm is extended to process a word graph on a single processor machine.

Full Paper

Bibliographic reference.  Zoltowski, Carla B. / Harper, Mary P. / Jamieson, Leah H. / Helzerman, Randall A. (1992): "PARSEC: a constraint-based framework for spoken language understanding", In ICSLP-1992, 249-252.