@inproceedings{robichaud2014hypotheses,
author = {Robichaud, Jean-Philippe and Crook, Paul A. and Xu, Puyang and Khan, Omar Zia and Sarikaya, Ruhi},
title = {Hypotheses Ranking for Robust Domain Classification And Tracking in Dialogue Systems},
booktitle = {Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)},
year = {2014},
month = {September},
abstract = {We present a novel application of hypothesis ranking (HR) for the task of domain detection in a multi-domain, multiturn dialog system. Alternate, domain dependent, semantic frames from a spoken language understanding (SLU) analysis are ranked using a gradient boosted decision trees (GBDT) ranker to determine the most likely domain. The ranker, trained using Lambda Rank, makes use of a range of signals derived from the SLU and previous turn context to improve domain detection. On a multi-turn corpus we show that this approach offers accuracy improvements of 3.2% absolute (25.6% relative) compared to relying solely on upfront non-contextual SLU domain models and 2.9% (24.5% relative) improvement even with contextual SLU domain models. We also show that HR can be trained to be robust to changes in the SLU.},
publisher = {ISCA - International Speech Communication Association},
url = {http://approjects.co.za/?big=en-us/research/publication/hypotheses-ranking-for-robust-domain-classification-and-tracking-in-dialogue-systems/},
edition = {Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)},
}