Please use this identifier to cite or link to this item: doi:10.22028/D291-25123
Title: Improving parsing by incorporating "prosodic clause boundaries" into a grammar
Author(s): Bakenecker, G.
Block, U.
Batliner, Anton
Kompe, Ralf
Nöth, Elmar
Regel-Brietzmann, P.
Language: English
Year of Publication: 1994
OPUS Source: Saarbrücken, 1994
SWD key words: Künstliche Intelligenz
DDC notations: 004 Computer science, internet
Publikation type: Report
Abstract: In written language, punctuation is used to separate main and subordinate clause. In spoken language, ambiguities arise due to missing punctuation, but clause boundaries are often marked prosodically and can be used instead. We detect PCBs (Prosodically markedClauseBoundaries) by using prosodic features (duration, intonation, energy, and pause information) with a neural network, achieving a recognition rate of 82%. PCBs are integrated into our grammar using a special syntactic category "break" that can be used in the phrase-structure rules of the grammar in a similar way as punctuation is used in grammars for written language. Whereas punctuation in most cases is obligatory, PCBs are sometimes optional. Moreover, they can in principle occur everywhere in the sentence due e.g. to hesitations or misrecognition. To cope with these problems we tested two different approaches: A slightly modified parser for word chains containing PCBs and a word graph parser that takes the probabilities of PCBs into account. Tests were conducted on a subset of infinitive subordinate clauses from a large speech database containing sentences from the domain of train table inquiries. The average number of syntactic derivations could be reduced by about 70 % even when working on recognized word graphs.
Link to this record: urn:nbn:de:bsz:291-scidok-40752
Series name: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Series volume: 37
Date of registration: 3-Aug-2011
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 SizeFormat 
report_37_94.pdf104,75 kBAdobe PDFView/Open

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.