Query by documents on top of a search interface

作者：

Highlights：

• A principled solution to querying by a document set on top of a search interface

• Applications such as Competitors Keywords problem and retrieving similar documents

• The solution accounts for the statistical properties of the document collection

• Only needs estimated collection statistics achievable by various sampling techniques

摘要

•A principled solution to querying by a document set on top of a search interface•Applications such as Competitors Keywords problem and retrieving similar documents•The solution accounts for the statistical properties of the document collection•Only needs estimated collection statistics achievable by various sampling techniques

论文关键词：Query by documents,Similarity search,Document search,Competitor keyword,Keyword discovery

论文评审过程：Received 5 November 2018, Revised 1 April 2020, Accepted 30 April 2021, Available online 14 May 2021, Version of Record 27 May 2021.

论文官网地址：https://doi.org/10.1016/j.is.2021.101793