Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent's performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.

中文翻译：

---

生成式对话网络

受到元学习和生成式教学网络最近工作的启发，我们提出了一个称为生成对话网络的框架，其中对话代理学习生成自己的标记训练数据（给定一些种子数据），然后从该数据中训练自己以执行给定的任务。我们使用强化学习来优化数据生成过程，其中奖励信号是代理在任务上的表现。任务可以是任何与语言相关的任务，从意图检测到完整的面向任务的对话。在这项工作中，我们表明我们的方法能够从种子数据中进行泛化，并且在有限的数据和有限的计算设置中表现良好，在多个数据集的意图检测和槽标记方面取得了显着的收益：ATIS、TOD、SNIPS 和 Restaurant8k。我们显示，与从种子数据训练的基线模型相比，意图检测平均提高了 35%，插槽标记平均提高了 21%。我们还对生成的数据的新颖性进行了分析，并提供了用于意图检测、插槽标记和非目标导向对话的生成示例。