This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues. We utilize the pre-trained multi-context ConveRT model for context representation in a model trained from scratch; and leverage the immediate preceding user utterance for context generation in a model adapted from the pre-trained GPT-2. Both experiments with the MultiWOZ dataset show that contextual information encoded by pre-trained model improves the performance of response generation both in automatic metrics and human evaluation. Our presented contextual generator enables higher variety of generated responses that fit better to the ongoing dialogue. Analysing the context size shows that longer context does not automatically lead to better performance, but the immediate preceding user utterance plays an essential role for contextual generation. In addition, we also propose a re-ranker for the GPT-based generation model. The experiments show that the response selected by the re-ranker has a significant improvement on automatic metrics.
翻译:这项工作将关于通过预先培训模式编码的对话历史的信息与当前系统表述的含义结合起来,以便在面向任务的对话中实现背景语言生成。我们使用预先培训的多文本 ConveRT 模式,在从零开始培训的模型中进行背景代表;在经过培训的GPT-2模型中,利用前期用户直截了当的语句进行背景生成。与多 WOZ 数据集有关的两个实验都表明,通过预先培训模式编码的背景信息在自动计量和人文评价中都改善了反应生成的性能。我们介绍的背景生成者使得生成的响应能够更加多样,更适合正在进行的对话。分析上下文大小表明,较长的上下文并不自动导致更好的业绩,而是前期用户直截的语句为背景一代发挥了必不可少的作用。此外,我们还提议为基于GPT-2的生成模型重新排序。实验显示,重新排序者选择的响应在自动计量方面都有显著改进。