Paper Info
Title
Multi-Language Hypotheses Ranking And Domain Tracking For Open Domain Dialogue Systems
Abstract
Hypothesis ranking (HR) is an approach for improving the accuracy of both domain detection and tracking in multi-domain, multi-turn dialogue systems. This paper presents the results of applying a universal HR model to multiple dialogue systems, each of which are using a different language. It demonstrates that as the set of input features used by HR models are largely language independent a single, universal HR model can be used in place of language specific HR models with only a small loss in accuracy (average absolute gain of +3.55% versus +4.54%), and also such a model can generalise well to new unseen languages, especially related languages (achieving an average absolute gain of +2.8% in domain accuracy on held out locales fr-fr, es-es, it-it; an average of 66% of the gain that could be achieve by training language specific HR models). That the latter is achieved without retraining significantly eases expansion of existing dialogue systems to new locales/languages.
Year
Venue
Keywords
2015
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5
dialogue systems, natural language under-standing, hypothesis ranking, contextual domain classification, multi-language, locale expansion, language independence
Field
DocType
Citations 
Ranking,Computer science,Speech recognition,Absolute gain,Natural language processing,Artificial intelligence,Multi language,Retraining
Conference
2
PageRank 
References 
Authors
0.48
8
3
Name
Order
Citations
PageRank
Paul A. Crook192.26
Jean-Philippe Robichaud2121.98
Ruhi Sarikaya369864.49