Next Article in Journal
A Novel Approach to Energy Management with Power Quality Enhancement in Hydrogen Based Microgrids through Numerical Simulation
Previous Article in Journal
Influence of Curing Time on the Mechanical Behavior of Cold Recycled Bituminous Mix in Flexible Pavement Base Layer
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 14
Issue 17
10.3390/app14177614
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Enhancing Task-Oriented Dialogue Modeling through Coreference-Enhanced Contrastive Pre-Training

by
Yi Huang
*,
Si Chen
,
Yaqin Chen
,
Junlan Feng
* and
Chao Deng
JIUTIAN Team, China Mobile Research Institute, Beijing 100053, China
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2024, 14(17), 7614; https://doi.org/10.3390/app14177614
Submission received: 17 May 2024 / Revised: 12 July 2024 / Accepted: 14 July 2024 / Published: 28 August 2024
(This article belongs to the Section Computing and Artificial Intelligence)
Browse Figures
Versions Notes

Abstract

Pre-trained language models (PLMs) are proficient at understanding context in plain text but often struggle with the nuanced linguistics of task-oriented dialogues. The information exchanges in dialogues and the dynamic role-shifting of speakers contribute to complex coreference and interlinking phenomena across multi-turn interactions. To address these challenges, we propose Coreference-Enhanced Contrastive Pre-training (CECPT), an innovative pre-training framework specifically designed to enhance dialogue modeling. CECPT utilizes unsupervised dialogue datasets to capture both semantic richness and structural coherence. Our experimental results demonstrate that the CECPT model significantly outperforms established baselines in three critical applications: intent recognition, dialogue act prediction, and dialogue state tracking. These findings suggest that CECPT is more adept at following the information flow within dialogues and accurately linking statuses to their respective references.
Keywords: dialogue system; contrastive pre-training; graph modeling dialogue system; contrastive pre-training; graph modeling

Share and Cite

MDPI and ACS Style

Huang, Y.; Chen, S.; Chen, Y.; Feng, J.; Deng, C. Enhancing Task-Oriented Dialogue Modeling through Coreference-Enhanced Contrastive Pre-Training. Appl. Sci. 2024, 14, 7614. https://doi.org/10.3390/app14177614

AMA Style

Huang Y, Chen S, Chen Y, Feng J, Deng C. Enhancing Task-Oriented Dialogue Modeling through Coreference-Enhanced Contrastive Pre-Training. Applied Sciences. 2024; 14(17):7614. https://doi.org/10.3390/app14177614

Chicago/Turabian Style

Huang, Yi, Si Chen, Yaqin Chen, Junlan Feng, and Chao Deng. 2024. "Enhancing Task-Oriented Dialogue Modeling through Coreference-Enhanced Contrastive Pre-Training" Applied Sciences 14, no. 17: 7614. https://doi.org/10.3390/app14177614

APA Style

Huang, Y., Chen, S., Chen, Y., Feng, J., & Deng, C. (2024). Enhancing Task-Oriented Dialogue Modeling through Coreference-Enhanced Contrastive Pre-Training. Applied Sciences, 14(17), 7614. https://doi.org/10.3390/app14177614

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop