Please use this identifier to cite or link to this item:
doi:10.22028/D291-25318
Title: | Integrating syntactic and prosodic information for the efficient detection of empty categories |
Author(s): | Batliner, Anton Feldhaus, Anke Geißler, Stefan Kießling, Andreas Kiss, Tibor Kompe, Ralf Nöth, Elmar |
Language: | English |
Year of Publication: | 1996 |
SWD key words: | Künstliche Intelligenz |
Free key words: | artificial intelligence |
DDC notations: | 004 Computer science, internet |
Publikation type: | Report |
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 workload for the parser. |
Link to this record: | urn:nbn:de:bsz:291-scidok-53165 hdl:20.500.11880/25374 http://dx.doi.org/10.22028/D291-25318 |
Series name: | Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz] |
Series volume: | 113 |
Date of registration: | 13-Jun-2013 |
Faculty: | SE - Sonstige Einrichtungen |
Department: | SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
File | Description | Size | Format | |
---|---|---|---|---|
report_113_96.pdf | 162,37 kB | Adobe PDF | View/Open |
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.