训练无需回合级对话标注的零样本可泛化端到端任务型对话系统
Training Zero-Shot Generalizable End-to-End Task-Oriented Dialog System Without Turn-level Dialog Annotations
AI总结：
本工作通过多任务指令微调，在不使用回合级人工标注的情况下训练任务型对话系统，使其能自主检索外部信息并零样本泛化到新领域，性能超越有标注训练的模型和ChatGPT。
摘要：
任务型对话（TOD）系统使用户能够通过自然语言交互实现其目标。传统上，这些系统依赖于回合级的人工标注元数据，如对话状态和策略标注，这些标注昂贵、耗时，且常常不一致或容易出错。这种依赖性限制了利用大量现成对话数据来训练TOD系统的潜力。此外，TOD系统设计中的一个关键挑战是确定何时以及如何访问和整合来自外部来源的信息。当前方法通常期望这些信息与对话上下文一起提供，而不是学习自主识别和检索它们。虽然预训练的大语言模型（LLMs）已被用于开发TOD系统，但它们在没有繁琐标注的情况下训练此类系统的潜力在很大程度上仍未得到探索。本工作采用多任务指令微调来创建更高效、更可扩展的TOD系统，这些系统可以在没有人工标注的情况下有效利用自然语言对话数据，同时自主管理外部信息检索。我们使用三个不同的TOD数据集和三个不同规模的LLM进行了广泛的实验评估，结果表明我们的方法能够泛化到新的、未见过的领域。值得注意的是，我们的方法在性能上优于在标注数据上训练的最先进模型以及十亿级参数的现成ChatGPT模型。
英文摘要：
Task-oriented dialogue (TOD) systems enable users to achieve their goals through natural language interactions. Traditionally, these systems have relied on turn-level manually annotated metadata, such as dialogue states and policy annotations, which are expensive, time-consuming, and often inconsistent or error-prone. This dependence limits the potential to leverage vast amounts of readily available conversational data for training TOD systems. Additionally, a critical challenge in TOD system design is determining when and how to access and integrate information from external sources. Current approaches typically expect this information to be provided alongside the dialogue context, rather than learning to identify and retrieve it autonomously. While pre-trained large language models (LLMs) have been used to develop TOD systems, their potential to train such systems without laborious annotations remains largely unexplored. This work employs multi-task instruction fine-tuning to create more efficient and scalable TOD systems that can effectively leverage natural language conversational data without manual annotations, while autonomously managing external information retrieval. Our extensive experimental evaluations, using three diverse TOD datasets and three LLMs of varying sizes, demonstrate that our approach can generalize to new, unseen domains. Notably, our approach outperforms both state-of-the-art models trained on annotated data and billion-scale parameter off-the-shelf ChatGPT models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
