Global-Locally Self-Attentive Dialogue State Tracker

05/19/2018
by   Victor Zhong, et al.
0

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achieves state-of-the-art performance on the WoZ and DSTC2 state tracking tasks. GLAD obtains 88.1 outperforming prior work by 3.7 joint goal accuracy and 97.5 1.1

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2019

SIM: A Slot-Independent Neural Model for Dialogue State Tracking

Dialogue state tracking is an important component in task-oriented dialo...
research
12/03/2018

Toward Scalable Neural Dialogue State Tracking Model

The latency in the current neural based dialogue state tracking models p...
research
06/16/2022

Multimodal Dialogue State Tracking

Designed for tracking user goals in dialogues, a dialogue state tracker ...
research
02/03/2020

Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks

Spoken dialogue systems typically use a list of top-N ASR hypotheses for...
research
10/22/2019

Scalable Neural Dialogue State Tracking

A Dialogue State Tracker (DST) is a key component in a dialogue system a...
research
08/20/2019

Teacher-Student Framework Enhanced Multi-domain Dialogue Generation

Dialogue systems dealing with multi-domain tasks are highly required. Ho...
research
08/08/2020

Point or Generate Dialogue State Tracker

Dialogue state tracking is a key part of a task-oriented dialogue system...

Please sign up or login with your details

Forgot password? Click here to reset