Dialog state tracking, a machine reading approach using Memory Network
This addresses the problem of accurately estimating dialog status in end-to-end systems for natural language processing, though it appears incremental as it adapts an existing neural architecture to a specific task.
The paper tackles dialog state tracking by framing it as a machine reading task using an End-to-End Memory Network (MemN2N), achieving encouraging results on the DSTC-2 dataset and its extended version with added reasoning capabilities.
In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate a compact representation of the current dialog status from a sequence of noisy observations produced by the speech recognition and the natural language understanding modules. This paper introduces a novel method of dialog state tracking based on the general paradigm of machine reading and proposes to solve it using an End-to-End Memory Network, MemN2N, a memory-enhanced neural network architecture. We evaluate the proposed approach on the second Dialog State Tracking Challenge (DSTC-2) dataset. The corpus has been converted for the occasion in order to frame the hidden state variable inference as a question-answering task based on a sequence of utterances extracted from a dialog. We show that the proposed tracker gives encouraging results. Then, we propose to extend the DSTC-2 dataset with specific reasoning capabilities requirement like counting, list maintenance, yes-no question answering and indefinite knowledge management. Finally, we present encouraging results using our proposed MemN2N based tracking model.