Robust Parsing of Spoken Dialogue Using Contextual Knowledge and Recognition Probabilities

1995/05/08 by Gerhard Hanrieder, Hanrieder, Gerhard, Guenther Goerz +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cmp-lg #cs.CL

paper · pdf · doi:10.48550/arxiv.cmp-lg/9505017

4 pages, LaTex source, 3 PostScript figures, uses epsf.sty and ETRW.sty, to appear in Proceedings of ESCA Workshop on Spoken Dialogue Systems, Denmark, May 30-June 2

arxiv created 1995/05/08 · openalex publication_date 1995/05/08 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper we describe the linguistic processor of a spoken dialogue system. The parser receives a word graph from the recognition module as its input. Its task is to find the best path through the graph. If no complete solution can be found, a robust mechanism for selecting multiple partial results is applied. We show how the information content rate of the results can be improved if the selection is based on an integrated quality score combining word recognition scores and context-dependent semantic predictions. Results of parsing word graphs with and without predictions are reported.

Related

• Robust Grammatical Analysis for Spoken Dialogue Systems
• The role of robust semantic analysis in spoken language dialogue systems
• Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
• Parsing of Spoken Language under Time Constraints