Accurate statistical spoken language understanding from limited development resources
- 1 March 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 5021-5024
Abstract
Robust spoken language understanding (SLU) is a key component of spoken dialogue systems. Recent statistical approaches to this problem require additional resources (e.g. gazetteers, grammars, syntactic treebanks) which are expensive and time-consuming to produce and maintain. However, simple datasets annotated only with slot-values are commonly used in dialogue systems development, and are easy to collect, automatically annotate, and update. We show that it is possible to reach state-of-the-art performance using minimal additional resources, by using Markov logic networks (MLNs). We also show that performance can be further improved by exploiting long distance dependencies between slot-values. For example, by representing such features in MLNs, but without using a gazetteer, we outperform the hidden vector state (HVS) model of He and Young 2006 (1.26% improvement, a 13% error reduction).Keywords
This publication has 5 references indexed in Scilit:
- Spoken language understanding using the Hidden Vector State ModelSpeech Communication, 2006
- Markov logic networksMachine Learning, 2006
- Incremental integer linear programming for non-projective dependency parsing2006
- The AT&T spoken language understanding systemIEEE Transactions on Audio, Speech, and Language Processing, 2005
- Context-sensitive spoken dialogue processing with the DOP modelNatural Language Engineering, 1999