Construction of Hierarchical Structured Knowledge-based Recommendation Dialogue Dataset and Dialogue System
Construction of Hierarchical Structured Knowledge-based Recommendation Dialogue Dataset and Dialogue System
复制标题
DOI：
10.18653/v1/2022.dialdoc-1.9
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Takashi Kodama;Ribeka Tanaka;S. Kurohashi
中科院分区：
文献类型：
--
作者：
Takashi Kodama;Ribeka Tanaka;S. Kurohashi
我们开发推荐对话系统来帮助用户了解某些目标的吸引力（例如，电影）。在这样的对话中，推荐系统需要利用结构化的外部知识来提供信息丰富和详细的推荐。然而，没有具有结构化外部知识的对话数据集，旨在为目标提供详细的建议。因此，我们构建了一个对话数据集，日本电影推荐对话（JMRD），其中推荐器在长对话（平均23转）中推荐一部电影。该数据集中使用的外部知识是分层结构的，包括标题、演员阵容、评论和情节。每个推荐者的话语都与与该话语相关的外部知识相关联。然后，我们创建了一个电影推荐对话系统，考虑了外部知识的结构和使用的知识的历史。实验结果表明，该模型在知识选择方面优于基线模型，具有上级的特点。
We work on a recommendation dialogue system to help a user understand the appealing points of some target (e.g., a movie). In such dialogues, the recommendation system needs to utilize structured external knowledge to make informative and detailed recommendations. However, there is no dialogue dataset with structured external knowledge designed to make detailed recommendations for the target. Therefore, we construct a dialogue dataset, Japanese Movie Recommendation Dialogue (JMRD), in which the recommender recommends one movie in a long dialogue (23 turns on average). The external knowledge used in this dataset is hierarchically structured, including title, casts, reviews, and plots. Every recommender’s utterance is associated with the external knowledge related to the utterance. We then create a movie recommendation dialogue system that considers the structure of the external knowledge and the history of the knowledge used. Experimental results show that the proposed model is superior in knowledge selection to the baseline models.