论文标题
面向目标对话系统的上下文感知语言建模
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
论文作者
论文摘要
面向目标的对话系统面临着流利的语言产生和特定于任务的控制之间的权衡。尽管使用大型语言模型进行监督的学习能够产生现实的文本，但如何在不牺牲语言质量的情况下指导此类回答是完成特定任务的问题仍然是一个悬而未决的问题。在这项工作中，我们将面向目标的对话作为部分观察到的马尔可夫决策过程，将语言模型解释为动态和策略的表示。这种观点使我们能够将技术从基于学习的控制（例如任务重新标记）扩展到以目标感知方式得出一种简单有效的方法来获得命运语言模型，从而显着改善了任务绩效。我们还引入了许多培训策略，以更好地将模型重点放在手头的任务上。我们在使用AirDialogue的实用飞行预订任务上评估了我们的方法，上下文感知语言模型（平静）。从经验上讲，在任务成功方面，平静的表现优于最先进的方法，与人类水平的任务绩效相匹配。
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task relabeling, to derive a simple and effective method to finetune language models in a goal-aware way, leading to significantly improved task performance. We additionally introduce a number of training strategies that serve to better focus the model on the task at hand. We evaluate our method, Context-Aware Language Models (CALM), on a practical flight-booking task using AirDialogue. Empirically, CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance.
