Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are commonly designed to generate responses given the user's utterances in natural language. One main challenge is that these generated responses both have to be appropriate for the given dialog context and must be grammatically and semantically correct. An alternative to such generation-based approaches is to retrieve responses from pre-recorded dialog data and to adapt them if needed. Such retrieval-based approaches were successfully explored in the context of general conversational systems, but have received limited attention in recent years for CRS. In this work, we re-assess the potential of such approaches and design and evaluate a novel technique for response retrieval and ranking. A user study (N=90) revealed that the responses by our system were on average of higher quality than those of two recent generation-based systems. We furthermore found that the quality ranking of the two generation-based approaches is not aligned with the results from the literature, which points to open methodological questions. Overall, our research underlines that retrieval-based approaches should be considered an alternative or complement to language generation approaches.
翻译:最近的方法依靠在人与人之间记录的对话中经过培训的神经模型,实施端对端学习过程。这些系统通常设计为根据用户自然语言的发声生成响应。一个主要挑战是,这些生成的响应必须适合特定对话环境,而且必须在语法和语义上正确。这种基于一代的方法的替代办法是检索预先记录的对话数据中的答复,并在必要时加以调整。这些基于检索的方法在一般对口系统范围内得到成功探索,但近年来CRS受到的关注有限。在这项工作中,我们重新评估了这些方法的潜力,设计并评价了一种用于回复检索和排序的新技术。用户研究(N=90)显示,我们系统的反应平均质量高于最近两个基于一代的系统。我们进一步发现,两种基于一代的方法的质量等级与替代文献的结果不一致,这些结果指向开放的方法问题。总体而言,我们的研究强调,应当将这种方法与新一代方法加以补充。