Discriminative spoken language understanding using word confusion networks
Authors:
- 1 December 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 176-181
Abstract
Current commercial dialogue systems typically use hand-crafted grammars for Spoken Language Understanding (SLU) operating on the top one or two hypotheses output by the speech recogniser. These systems are expensive to develop and they suffer from significant degradation in performance when faced with recognition errors. This paper presents a robust method for SLU based on features extracted from the full posterior distribution of recognition hypotheses encoded in the form of word confusion networks. Following [1], the system uses SVM classifiers operating on n-gram features, trained on unaligned input/output pairs. Performance is evaluated on both an off-line corpus and on-line in a live user trial. It is shown that a statistical discriminative approach to SLU operating on the full posterior ASR output distribution can substantially improve performance both in terms of accuracy and overall dialogue reward. Furthermore, additional gains can be obtained by incorporating features from the previous system output.Keywords
This publication has 13 references indexed in Scilit:
- Learning Conditional Random Fields from Unaligned Data for Natural Language Understanding2011
- Bayesian update of dialogue state: A POMDP framework for spoken dialogue systemsComputer Speech & Language, 2010
- Spoken language understanding from unaligned data using discriminative classification models2009
- Accurate statistical spoken language understanding from limited development resources2008
- Partially observable Markov decision processes for spoken dialog systemsComputer Speech & Language, 2007
- Beyond ASR 1-best: Using word confusion networks in spoken language understandingComputer Speech & Language, 2006
- Spoken language understanding using the Hidden Vector State ModelSpeech Communication, 2006
- Using string-kernels for learning semantic parsers2006
- Language understanding using hidden understanding models2002
- Finding consensus in speech recognition: word error minimization and other applications of confusion networksComputer Speech & Language, 2000