Published on Tue Jun 23 2015

Multi-domain Dialog State Tracking using Recurrent Neural Networks

Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gašić, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve Young

dialog data drawn from different dialog domains can be used to train a general belief tracking model. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains.

0
0
0
Abstract

Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model.

Sun Aug 20 2017
NLP
An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
We present a novel end-to-end trainable neural network model for task-oriented dialog systems. The model is able to track dialog state, issueAPI calls to knowledge base (KB), and incorporate structured KB query results into system responses.
0
0
0
Tue Feb 21 2017
NLP
Hybrid Dialog State Tracker with ASR Features
This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slot-filling dialog systems. Our architecture is inspired by previously proposed neural-network-based belief-tracking systems.
0
0
0
Mon Oct 28 2019
Machine Learning
A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems
The goal of dialog state tracking (DST) is to monitor the state of the conversation from the dialog history. Despite theirimpressive performance, current neural architectures for DST are typicallyavily-engineered and conceptually complex. In this work, we propose asimple but effective
0
0
0
Tue Jul 18 2017
NLP
Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking
This paper presents our novel method to encode word confusion networks, which can represent a rich hypothesis space of automatic speech recognition systems. We demonstrate the utility of our approach for the task of dialog state tracking in spoken dialog systems.
0
0
0
Mon Jul 13 2015
NLP
Incremental LSTM-based Dialog State Tracker
An incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses. We also present the key non-standard aspects of the model.
0
0
0
Sun Jun 12 2016
NLP
Neural Belief Tracker: Data-Driven Dialogue State Tracking
Most current approaches have difficulty scaling to larger, more complex dialogue domains. We propose a novel Neural Belief Tracking (NBT)framework which overcomes these problems. NBT models reason over pre-trained word vectors,learning to compose them into distributed representations of user utterances and dialogue context.
1
0
0