Integrating Syntactic and Prosodic Information for the Efficient Detection of Empty Categories
cmp-lg
2008-02-03 v1 Computation and Language
Abstract
We describe a number of experiments that demonstrate the usefulness of prosodic information for a processing module which parses spoken utterances with a feature-based grammar employing empty categories. We show that by requiring certain prosodic properties from those positions in the input where the presence of an empty category has to be hypothesized, a derivation can be accomplished more efficiently. The approach has been implemented in the machine translation project VERBMOBIL and results in a significant reduction of the work-load for the parser.
Cite
@article{arxiv.cmp-lg/9607004,
title = {Integrating Syntactic and Prosodic Information for the Efficient Detection of Empty Categories},
author = {Anton Batliner and Anke Feldhaus and Stefan Geissler and Andreas Kiessling and Tibor Kiss and Ralf Kompe and Elmar Noeth},
journal= {arXiv preprint arXiv:cmp-lg/9607004},
year = {2008}
}
Comments
To appear in the Proceedings of Coling 1996, Copenhagen. 6 pages