A neural graph embedding approach for selecting review sentences
作者：
Highlights：
• We address the problem of cold products that do not have sufficient reviews.
• We generate reviews for cold products by their association to reviews of warm products.
• We model products, users, reviews and their interactions in the form of a graph.
• We derive the representation of the nodes to learn products and reviews associations.
• Our evaluations show that our work outperforms the state of the art methods.
摘要
•We address the problem of cold products that do not have sufficient reviews.•We generate reviews for cold products by their association to reviews of warm products.•We model products, users, reviews and their interactions in the form of a graph.•We derive the representation of the nodes to learn products and reviews associations.•Our evaluations show that our work outperforms the state of the art methods.
论文关键词：Cold-start,Graph-based information retrieval,Neural embeddings,Summarization
论文评审过程：Received 14 December 2018, Revised 3 October 2019, Accepted 21 October 2019, Available online 16 December 2019, Version of Record 23 January 2020.
论文官网地址：https://doi.org/10.1016/j.elerap.2019.100917
