Learning from homologous queries and semantically related terms for query auto completion
作者：
Highlights：
•
• We propose a learning to rank based query auto completion model (L2R-QAC) that exploits contributions from so-called homologous queries for a QAC candidate, in which two kinds of homologous queries are taken into account.
• We propose semantic features for QAC, using the semantic relatedness of terms inside a query candidate and of pairs of terms from a candidate and from queries previously submitted in the same session.
• We analyze the effectiveness of our L2R-QAC model with newly added features, and find that it significantly outperforms state-of-the-art QAC models, either based on learning to rank or on popularity.
摘要
•We propose a learning to rank based query auto completion model (L2R-QAC) that exploits contributions from so-called homologous queries for a QAC candidate, in which two kinds of homologous queries are taken into account.•We propose semantic features for QAC, using the semantic relatedness of terms inside a query candidate and of pairs of terms from a candidate and from queries previously submitted in the same session.•We analyze the effectiveness of our L2R-QAC model with newly added features, and find that it significantly outperforms state-of-the-art QAC models, either based on learning to rank or on popularity.
论文关键词：Query auto completion,Semantics,Query suggestion,Learning to rank
论文评审过程：Received 27 April 2015, Revised 26 November 2015, Accepted 1 December 2015, Available online 12 January 2016, Version of Record 17 May 2016.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.12.008
