State-of-the-art methods on conversational recommender systems (CRS) leverage external knowledge to enhance both items' and contextual words' representations to achieve high quality recommendations and responses generation. However, the representations of the items and words are usually modeled in two separated semantic spaces, which leads to misalignment issue between them. Consequently, this will cause the CRS to only achieve a sub-optimal ranking performance, especially when there is a lack of sufficient information from the user's input. To address limitations of previous works, we propose a new CRS framework KLEVER, which jointly models items and their associated contextual words in the same semantic space. Particularly, we construct an item descriptive graph from the rich items' textual features, such as item description and categories. Based on the constructed descriptive graph, KLEVER jointly learns the embeddings of the words and items, towards enhancing both recommender and dialog generation modules. Extensive experiments on benchmarking CRS dataset demonstrate that KLEVER achieves superior performance, especially when the information from the users' responses is lacking.

翻译：当前对话推荐系统（CRS）的前沿方法借助外部知识来增强项目与上下文词汇的表示，从而实现高质量推荐与响应生成。然而，这些项目与词汇的表示通常建模在两个分离的语义空间中，导致二者间的对齐问题。这进而使CRS在缺乏用户输入充足信息时，难以达到最优排序性能。为克服现有工作的局限性，我们提出新型CRS框架KLEVER，该框架在同一语义空间中联合建模项目及其相关上下文词汇。具体而言，我们利用丰富的项目文本特征（如项目描述与类别）构建项目描述性图谱。基于所构建的描述性图谱，KLEVER联合学习词汇与项目的嵌入表示，从而增强推荐与对话生成两个模块的性能。在标准CRS数据集上的大量实验表明，KLEVER实现了卓越性能，尤其在用户响应信息不足时表现更为突出。