Formal language models for finding groups of experts
作者：
Highlights：
• We introduce a new information retrieval task: given a topic, try to find knowledgeable groups that have expertise on the topic.
• Five probabilistic language models are proposed to tackle the challenge of automatically finding groups of experts in heterogeneous document collections.
• For evaluation purpose, a data set is created based on a publicly downloadable corpus used in the TREC Enterprise 2005 and 2006 tracks and three types of ground truth are defined.
• We provide a detailed analysis of the performance of the proposed group finding models.
摘要
•We introduce a new information retrieval task: given a topic, try to find knowledgeable groups that have expertise on the topic.•Five probabilistic language models are proposed to tackle the challenge of automatically finding groups of experts in heterogeneous document collections.•For evaluation purpose, a data set is created based on a publicly downloadable corpus used in the TREC Enterprise 2005 and 2006 tracks and three types of ground truth are defined.•We provide a detailed analysis of the performance of the proposed group finding models.
论文关键词：Group finding,Entity retrieval,Enterprise search
论文评审过程：Received 24 December 2014, Revised 10 October 2015, Accepted 25 November 2015, Available online 2 February 2016, Version of Record 17 May 2016.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.11.005
