Work

Domain-specific Attention with Distributional Signatures for Multi-Domain End-to-end Task-Oriented Dialogue

Year: 2023

Type: conference-paper

Abstract: The end-to-end task-oriented dialogue system has achieved great success in recent years.Most of these dialogue systems need to accommodate multi-domain dialogue in real-world scenarios.However, due to the high cost of dialogue data annotation and the scarcity of labeled dialogue data, existing methods are difficult to extend to new domains.Therefore, it is essential to use limited data to construct multi-domain dialogue systems.To solve this problem, we propose a novel domain attention module.It uses distributional signatures to construct a multi-domain dialogue system effectively with limited data, which has strong extensibility.We also define an adjacent n-gram pattern to explore potential patterns for dialogue entities.Experimental results show that our approach outperforms the baseline models on most metrics.In the few-shot scenario, we show our method gets a great improvement compared with previous methods while keeping a smaller model scale.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2023.findings-acl.194

Authors: Xing Ma, Peng Zhang, Feifei Zhao

Institution: Tianjin University

Language: English

Topic: Speech and dialogue systems

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Natural Science Foundation of China

OpenAlex ID: W4385572078