IWSDS 2016: 13-16, 2016

Julien PerezProbabilistic matching for dialog state tracking with limited training data

Abstract: This report details our submission to the fourth Dialog State Tracking Challence (DSTC4), the first time Xerox has participated. Accordingly, we have taken an segment-specific approach that attempts to identify ontology values as precisely as possible using a statistical model. Our model is inspired by work in Named Entity Linking that extracts mentions, then searches and reranks candidates. This is mainly motivated by the small amount of data available relative to the high complexity of the task. However, we believe this setting is realistic in the industrial environment where few data are generally available for a given dialog context to automate. This relatively simple approach performs reasonably at 38.5% F1 using schedule 2 evaluation, and is the most precise at 59.4% on the DSTC4 test set.