Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation

Abstract

A challenge in the Dialogue State Tracking (DST) field is adapting models to new domains without using any supervised data — zero-shot domain adaptation. Parameter-Efficient Transfer Learning (PETL) has the potential to address this problem due to its robustness. However, it has yet to be applied to the zero-shot scenarios, as it is not clear how to apply it unsupervisedly. Our method, Prompter, uses descriptions of target domain slots to generate dynamic prefixes that are concatenated to the key and values at each layer′s self-attention mechanism. This allows for the use of prefix-tuning in zero-shot. Prompter outperforms previous methods on both the MultiWOZ and SGD benchmarks. In generating prefixes, our analyses find that Prompter not only utilizes the semantics of slot descriptions but also how often the slots appear together in conversation. Moreover, Prompter′s gains are due to its improved ability to distinguish ″none″-valued dialogue slots, compared against baselines.

Publication
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Ibrahim Taha Aksu
Doctoral Alumnus (‘24)

Doctoral Alumni (‘24)

Min-Yen Kan
Min-Yen Kan
Associate Professor

WING lead; interests include Digital Libraries, Information Retrieval and Natural Language Processing.