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.
翻译:以任务为导向的对话跟踪(DST)是任务为导向的对话系统的一个关键组成部分,它通过确定当前对话中预先确定的空档的值来代表用户的意图。现有方法使用手工制作的模板和额外空档信息来微调和推动大型预先培训的语言模式,并从对话中获取空档值。设计有效的快讯需要大量手工和域知识,限制这些方法在新领域和新任务中的通用性。在这项工作中,我们提议DSTT是一种通用的文本调整方法,为特定对话检索高度相关的培训实例,以便在没有手工制作的模板的情况下微调模型。对多 WOZ基准数据集的实验显示,DistractICT利用一个小得多的模式,超越了各种零点和几点环境中的现有方法,从而为往往资源有限的现实世界部署提供了重要优势。