Combining statistical and knowledge-based spoken language understanding in conditional models

Authors:
Ye-Yi Wang;Alex Acero;Milind Mahajan;John Lee
Affiliations:
Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Spoken Language Systems, Cambridge, MA
Venue:
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Year:
2006

Citing 4
Cited 2

Evaluation of spoken language systems: the ATIS domain

HLT '90 Proceedings of the workshop on Speech and Natural Language
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Accelerated training of conditional random fields with stochastic gradient methods

ICML '06 Proceedings of the 23rd international conference on Machine learning

Spoken language understanding using weakly supervised learning

Computer Speech and Language
Discriminative framework for spoken tunisian dialect understanding

SLSP'13 Proceedings of the First international conference on Statistical Language and Speech Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Spoken Language Understanding (SLU) addresses the problem of extracting semantic meaning conveyed in an utterance. The traditional knowledge-based approach to this problem is very expensive --- it requires joint expertise in natural language processing and speech recognition, and best practices in language engineering for every new domain. On the other hand, a statistical learning approach needs a large amount of annotated data for model training, which is seldom available in practical applications outside of large research labs. A generative HMM/CFG composite model, which integrates easy-to-obtain domain knowledge into a data-driven statistical learning framework, has previously been introduced to reduce data requirement. The major contribution of this paper is the investigation of integrating prior knowledge and statistical learning in a conditional model framework. We also study and compare conditional random fields (CRFs) with perceptron learning for SLU. Experimental results show that the conditional models achieve more than 20% relative reduction in slot error rate over the HMM/CFG model, which had already achieved an SLU accuracy at the same level as the best results reported on the ATIS data.