Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking

08/21/2019
by   Qingbin Liu, et al.
0

Dialogue state tracking (DST) is an essential component in task-oriented dialogue systems, which estimates user goals at every dialogue turn. However, most previous approaches usually suffer from the following problems. Many discriminative models, especially end-to-end (E2E) models, are difficult to extract unknown values that are not in the candidate ontology; previous generative models, which can extract unknown values from utterances, degrade the performance due to ignoring the semantic information of pre-defined ontology. Besides, previous generative models usually need a hand-crafted list to normalize the generated values. How to integrate the semantic information of pre-defined ontology and dialogue text (heterogeneous texts) to generate unknown values and improve performance becomes a severe challenge. In this paper, we propose a Copy-Enhanced Heterogeneous Information Learning model with multiple encoder-decoder for DST (CEDST), which can effectively generate all possible values including unknown values by copying values from heterogeneous texts. Meanwhile, CEDST can effectively decompose the large state space into several small state spaces through multi-encoder, and employ multi-decoder to make full use of the reduced spaces to generate values. Multi-encoder-decoder architecture can significantly improve performance. Experiments show that CEDST can achieve state-of-the-art results on two datasets and our constructed datasets with many unknown values.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/22/2018

Towards Universal Dialogue State Tracking

Dialogue state tracking is the core part of a spoken dialogue system. It...
research
07/25/2021

Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking

Recently, researchers have explored using the encoder-decoder framework ...
research
09/02/2019

Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation

Existing approaches to dialogue state tracking rely on pre-defined ontol...
research
05/03/2018

An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking

We highlight a practical yet rarely discussed problem in dialogue state ...
research
08/06/2019

Flexibly-Structured Model for Task-Oriented Dialogues

This paper proposes a novel end-to-end architecture for task-oriented di...
research
10/24/2020

Multi-Domain Dialogue State Tracking – A Purely Transformer-Based Generative Approach

We investigate the problem of multi-domain Dialogue State Tracking (DST)...
research
10/03/2020

Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

For multi-turn dialogue rewriting, the capacity of effectively modeling ...

Please sign up or login with your details

Forgot password? Click here to reset