Subtopic mining using simple patterns and hierarchical structure of subtopic candidates from web documents
作者：
Highlights：
•
• We use only web document collection instead of query logs and external resources.
• Our simple patterns are based on noun phrases and alternative partial-queries.
• We maintain a balance between popularity and diversity of subtopics.
• Our method covered various search intentions of a query by its few subtopics.
• Our results were steadily improved by extracting more relevant and various subtopics.
摘要
•We use only web document collection instead of query logs and external resources.•Our simple patterns are based on noun phrases and alternative partial-queries.•We maintain a balance between popularity and diversity of subtopics.•Our method covered various search intentions of a query by its few subtopics.•Our results were steadily improved by extracting more relevant and various subtopics.
论文关键词：Search intention,Subtopic mining,Hierarchical structure
论文评审过程：Received 29 October 2014, Revised 2 July 2015, Accepted 6 July 2015, Available online 28 August 2015, Version of Record 28 August 2015.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.07.001
