Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples

TL;DR

This paper introduces CombiSearch, a novel method for selecting in-context examples in dialogue state tracking that considers their combined impact, leading to significant improvements in data efficiency and DST performance.

Contribution

CombiSearch is a new approach that scores in-context examples based on their combinatorial effect on DST, surpassing state-of-the-art retrievers and improving performance.

Findings

Achieves 20x data efficiency gain on MultiWOZ

Generalizes well to SGD dataset

Attains 12% absolute improvement in upper bound DST performance

Abstract

In dialogue state tracking (DST), in-context learning comprises a retriever that selects labeled dialogues as in-context examples and a DST model that uses these examples to infer the dialogue state of the query dialogue. Existing methods for constructing training data for retrievers suffer from three key limitations: (1) the synergistic effect of examples is not considered, (2) the linguistic characteristics of the query are not sufficiently factored in, and (3) scoring is not directly optimized for DST performance. Consequently, the retriever can fail to retrieve examples that would substantially improve DST performance. To address these issues, we present CombiSearch, a method that scores effective in-context examples based on their combinatorial impact on DST performance. Our evaluation on MultiWOZ shows that retrievers trained with CombiSearch surpass state-of-the-art models, achieving a 20x gain in data efficiency and generalizing well to the SGD dataset. Moreover, CombiSearch attains a 12% absolute improvement in the upper bound DST performance over traditional approaches when no retrieval errors are assumed. This significantly increases the headroom for practical DST performance while demonstrating that existing methods rely on suboptimal data for retriever training.