Efficient Dialogue State Tracking by Selectively Overwriting Memory

11/10/2019
by   Sungdong Kim, et al.
0

Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches. However, they are computationally inefficient in that they predict the dialogue state at every turn from scratch. In this paper, we consider dialogue state as an explicit fixed-sized memory, and propose a selectively overwriting mechanism for more efficient DST. This mechanism consists of two steps: (1) predicting state operation on each of the memory slots, and (2) overwriting the memory with new values, of which only a few are generated according to the predicted state operations. Moreover, reducing the burden of the decoder by decomposing DST into two sub-tasks and guiding the decoder to focus only one of the tasks enables a more effective training and improvement in the performance. As a result, our proposed SOM-DST (Selectively Overwriting Memory for Dialogue State Tracking) achieves state-of-the-art joint goal accuracy with 51.38 MultiWOZ 2.1 in an open vocabulary-based DST setting. In addition, a massive gap between the current accuracy and the accuracy when ground truth operations are given suggests that improving the performance of state operation prediction is a promising research direction of DST.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/26/2023

Diable: Efficient Dialogue State Tracking as Operations on Tables

Sequence-to-sequence state-of-the-art systems for dialogue state trackin...
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
10/22/2018

Towards Universal Dialogue State Tracking

Dialogue state tracking is the core part of a spoken dialogue system. It...
research
04/07/2020

Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking

Dialogue state tracking (DST) aims at estimating the current dialogue st...
research
02/19/2020

Non-Autoregressive Dialog State Tracking

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialog...
research
03/07/2022

Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Tracking

Dialogue state tracking (DST) aims to extract essential information from...
research
04/07/2022

Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances

Dialogue State Tracking (DST) is primarily evaluated using Joint Goal Ac...

Please sign up or login with your details

Forgot password? Click here to reset