DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning
This addresses the generalizability issue in DST for task-oriented conversation systems, offering a more resource-efficient solution for real-world deployments, though it is incremental as it builds on existing in-context tuning methods.
The paper tackles the problem of requiring manual effort and domain knowledge for designing prompts in Dialogue State Tracking (DST) by proposing DiSTRICT, a retriever-driven in-context tuning approach that eliminates hand-crafted templates. Experiments on MultiWOZ datasets show it outperforms existing methods in zero-shot and few-shot settings using a smaller model.
Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and additional slot information to fine-tune and prompt large pre-trained language models and elicit slot values from the dialogue context. Significant manual effort and domain knowledge is required to design effective prompts, limiting the generalizability of these approaches to new domains and tasks. In this work, we propose DiSTRICT, a generalizable in-context tuning approach for DST that retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates. Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings using a much smaller model, thereby providing an important advantage for real-world deployments that often have limited resource availability.