论文标题
朝着强大的在线对话响应一代
Towards Robust Online Dialogue Response Generation
论文作者
论文摘要
尽管预先训练的序列到序列模型在对话响应的产生方面取得了巨大的成功，但聊天机器人仍然会在现实世界实践中产生不一致的响应，尤其是在多转弯设置中。我们认为这可能是由于培训和现实世界测试之间的差异引起的。在培训时，聊天机器人通过黄金上下文生成响应，而它必须基于由用户话语和模型在现实世界测试中预测的话语组成的上下文生成。随着话语数量的增长，这种差异在多转弯环境中变得更加严重。在本文中，我们提出了一种基于分层抽样的方法，该方法包括话语级采样和半浓度级采样，以减轻差异，从而暗中增加对话连贯性。我们进一步采用强化学习和重新排列方法，分别在训练和推理过程中明确优化对话连贯性。经验实验表明，提出的方法在实际实践中提出的方法提高了聊天机器人的鲁棒性。
Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings. We argue that this can be caused by a discrepancy between training and real-world testing. At training time, chatbot generates the response with the golden context, while it has to generate based on the context consisting of both user utterances and the model predicted utterances during real-world testing. With the growth of the number of utterances, this discrepancy becomes more serious in the multi-turn settings. In this paper, we propose a hierarchical sampling-based method consisting of both utterance-level sampling and semi-utterance-level sampling, to alleviate the discrepancy, which implicitly increases the dialogue coherence. We further adopt reinforcement learning and re-ranking methods to explicitly optimize the dialogue coherence during training and inference, respectively. Empirical experiments show the effectiveness of the proposed methods for improving the robustness of chatbots in real practice.
