Global-Locally Self-Attentive Dialogue State Tracker

Victor Zhong, Caiming Xiong, Richard Socher
5/19/2018
cs.CLcs.AI

Official code: salesforce/glad (187 stars, BSD-3-Clause, PyTorch, last commit 2022-02-12).

Abstract

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% joint goal accuracy and 97.1% request accuracy on WoZ, outperforming prior work by 3.7% and 5.5%. On DSTC2, our model obtains 74.5% joint goal accuracy and 97.5% request accuracy, outperforming prior work by 1.1% and 1.0%.

View on arXivView PDF

Code Implementations(1)

salesforce/gladOfficial100%
PyTorchBSD-3-Clause

Global-Locally Self-Attentive Dialogue State Tracker

18741Python, DockerfileJun 11, 20184 years agoBSD-3-Clause
dialogue-systemsmachine-learningnatural-language-processingpytorch

Similar Papers

Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

88% match1 repo42022

Efficient Dialogue State Tracking by Selectively Overwriting Memory

86% match1 repo1522019

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

85% match1 repo3922019

Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking

84% match2023

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

84% match2023

Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs

84% match2025

Cite this paper

@article{zhong2018globallocally,
  title  = {Global-Locally Self-Attentive Dialogue State Tracker},
  author = {Victor Zhong and Caiming Xiong and Richard Socher},
  year   = {2018},
  eprint = {1805.09655},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1805.09655}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1805.09655.svg)](https://codeofpaper.com/paper/1805.09655)

Discussion