Spectral decomposition method of dialog state tracking via collective matrix factorization
Julien Perez

TL;DR
This paper presents a novel spectral decomposition method for dialog state tracking using collective matrix factorization, improving efficiency and performance in dialog systems.
Contribution
It introduces a bilinear algebraic decomposition model for dialog state tracking, offering an efficient inference schema and competitive results on DSTC-2.
Findings
Encouraging results on DSTC-2 dataset
Computational efficiency over previous methods
Competitive performance with state-of-the-art trackers
Abstract
The task of dialog management is commonly decomposed into two sequential subtasks: dialog state tracking and dialog policy learning. In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate the true dialog state from noisy observations produced by the speech recognition and the natural language understanding modules. The state tracking task is primarily meant to support a dialog policy. From a probabilistic perspective, this is achieved by maintaining a posterior distribution over hidden dialog states composed of a set of context dependent variables. Once a dialog policy is learned, it strives to select an optimal dialog act given the estimated dialog state and a defined reward function. This paper introduces a novel method of dialog state tracking based on a bilinear algebric decomposition model that provides an efficient inference schema through…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
