Accurate statistical spoken language understanding from limited development resources

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

• Type: Conference
• Year: 2008
• Where: ICASSP
• Authors: I. V. Meza-Ruiz, Sebastian Riedel, Oliver Lemon
• Keywords: Additional Resources, Dialogue Systems, ICASSP 2008, Signal Processing, Spoken Dialogue Systems