Neural embedding-based specificity metrics for pre-retrieval query performance prediction
作者:
Highlights:
• We show how specificity can be measured in the context of neural embeddings.
• We employ neural embedding-based specificity for performing query performance prediction.
• We publicly release two gold standard test collections for evaluating of term specificity metrics.
摘要
•We show how specificity can be measured in the context of neural embeddings.•We employ neural embedding-based specificity for performing query performance prediction.•We publicly release two gold standard test collections for evaluating of term specificity metrics.
论文关键词:Performance prediction,Neural embeddings,Ad hoc retrieval
论文评审过程:Received 7 November 2019, Revised 6 February 2020, Accepted 13 March 2020, Available online 8 April 2020, Version of Record 8 April 2020.
论文官网地址:https://doi.org/10.1016/j.ipm.2020.102248