Please use this identifier to cite or link to this item: doi:10.22028/D291-25304
Title: Spoken language processing in the hybrid connectionist architecture SCREEN
Author(s): Wermter, Stefan
Weber, Volker
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: In this paper we describe a robust, learning approach to spoken language understanding. Since interactively spoken and computationally analyzed language often contains many errors, robust connectionist networks are used for providing a flat screening analysis. A screening analysis is a shallow flat analysis based on category sequences at various syntactic, semantic and dialog levels. Rather than using tree or graph representations a screening analysis uses category sequences in order to support robustness and learning. This flat screening analysis is examined in the context of the system SCREEN (Symbolic Connectionist Robust EnterprisE for Natural language). Starting with the word hypotheses generated by a speech recognizer, we give an overview of the architecture, and illustrate the flat robust processing at the levels of syntax, semantics, and dialog acts. While early connectionist models were often limited to a single network and a small task, the hybrid connectionist SCREEN system is an important step towards exploring connectionist techniques in larger hybrid symbolic/connectionist environments and for real-world problemsBased on our experience with SCREEN, hybrid connectionist techniques show a lot of potential for supporting robustness in interactive spoken language processing.
Link to this record: urn:nbn:de:bsz:291-scidok-53300
Series name: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Series volume: 138
Date of registration: 12-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 SizeFormat 
report_138_96.pdf248,42 kBAdobe PDFView/Open

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