Dialog state tracking, a machine reading approach using Memory Network
نویسندگان
چکیده
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. A state tracking module is primarily meant to act as support for a dialog policy but it can also be used as support for dialog corpus summarization and other kinds of information extraction from transcription of dialogs. From a probabilistic view, this is achieved by maintaining a posterior distribution over hidden dialog states composed, in the simplest case, of a set of context dependent variables. Once a dialog policy is defined, deterministic or learnt, it is in charge of selecting 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 the general paradigm of machine reading and proposes to solve it using a memory-enhanced neural network architecture. We evaluate the proposed approach on the second Dialog State Tracking Challenge (DSTC-2) dataset that has been converted for the occasion in order to fit the relaxed assumption of a machine reading formulation where the true state is only provided at the very end of each dialog instead of providing the state updates at the utterance level. We show that the proposed tracker gives encouraging results. Finally, 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.
منابع مشابه
Hybrid Dialog State Tracker
This paper presents a hybrid dialog state tracker that combines a rule based and a machine learning based approach to belief state tracking. Therefore, we call it a hybrid tracker. The machine learning in our tracker is realized by a Long Short Term Memory (LSTM) network. To our knowledge, our hybrid tracker sets a new state-of-the-art result for the Dialog State Tracking Challenge (DSTC) 2 dat...
متن کاملGated End-to-End Memory Networks
Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks (MemN2N) have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namely multi-fact questionanswering, positional reasoning or dialog related tasks,...
متن کاملDissertation Proposal Dialog Management with Deep Neural Networks
This document is a dissertation proposal submitted in partial fulfillment of the requirements for the doctoral exams. Its purpose is to define the dissertation goals and summarize initial experiments. We propose a novel approach to dialog state tracking in spoken dialog systems based on long short-term memory recurrent neural neural networks. The proposed model allows incremental, word-by-word ...
متن کاملDialog state tracking using long short-term memory neural networks
Neural network based approaches have recently shown stateof-art performance in the Dialog State Tracking Challenge (DSTC). In DSTC, a tracker is used to assign a label to the state at each moment in an input sequence of a dialog. Specifically, deep neural networks (DNNs) and simple recurrent neural networks (RNNs) have significantly improved the performance of the dialog state tracking. In this...
متن کاملDialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking
One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilisti...
متن کامل