A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
Safa A, Şahin GG (2025)
Publication Type: Conference contribution
Publication year: 2025
Publisher: Association for Computational Linguistics (ACL)
Book Volume: 1
Pages Range: 7562-7579
Conference Proceedings Title: Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies: Long Papers, NAACL-HLT 2025
Event location: Hybrid, Albuquerque, NM, USA
ISBN: 9798891761896
DOI: 10.18653/v1/2025.naacl-long.387
Abstract
Dialogue State Tracking (DST) is crucial for understanding user needs and executing appropriate system actions in task-oriented dialogues. Majority of existing DST methods are designed to work within predefined ontologies and assume the availability of gold domain labels, struggling with adapting to new slots values. While Large Language Models (LLMs)-based systems show promising zero-shot DST performance, they either require extensive computational resources or they underperform existing fully-trained systems, limiting their practicality. To address these limitations, we propose a zero-shot, open-vocabulary system that integrates domain classification and DST in a single pipeline. Our approach includes reformulating DST as a question-answering task for less capable models and employing self-refining prompts for more adaptable ones. Our system does not rely on fixed slot values defined in the ontology allowing the system to adapt dynamically. We compare our approach with existing SOTA, and show that it provides up to 20% better Joint Goal Accuracy (JGA) over previous methods on datasets like MultiWOZ 2.1, with up to 90% fewer requests to the LLM API. The source code is provided for reproducibility.
Involved external institutions
Turkey (TR)How to cite
APA:
Safa, A., & Şahin, G.G. (2025). A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding. In Luis Chiruzzo, Alan Ritter, Lu Wang (Eds.), Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies: Long Papers, NAACL-HLT 2025 (pp. 7562-7579). Hybrid, Albuquerque, NM, USA: Association for Computational Linguistics (ACL).
MLA:
Safa, Abdulfattah, and Gözde Gül Şahin. "A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding." Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2025, Hybrid, Albuquerque, NM, USA Ed. Luis Chiruzzo, Alan Ritter, Lu Wang, Association for Computational Linguistics (ACL), 2025. 7562-7579.
BibTeX: Download