Accurate Statistical Spoken Language Understanding from Limited Development Resources

Ivan Meza-Ruiz and Sebastian Riedel and Oliver Lemon


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 inMLNs, butwithout using a gazetteer, we outperform the Hidden Vector State (HVS) model of He and Young 2006 (1.26% improvement, a 13% error reduction).


Paper (PDF)