A probabilistic framework for integrating sentence-level semantics via BERT into pseudo-relevance feedback

作者：

Highlights：

• We propose a probabilistic framework integrating sentence-level semantic into PRF for expanding terms which are more semantically consistent with the query.

• Three enhanced models are generated by applying the probability framework to Rocchio-based PRF models.

• Experimental results highlight the proposed framework is robust and effective.

摘要

•We propose a probabilistic framework integrating sentence-level semantic into PRF for expanding terms which are more semantically consistent with the query.•Three enhanced models are generated by applying the probability framework to Rocchio-based PRF models.•Experimental results highlight the proposed framework is robust and effective.

论文关键词：Latent semantic information,Information retrieval,Query expansion,Text similarity,Pseudo-relevance feedback

论文评审过程：Received 9 August 2021, Accepted 24 August 2021, Available online 27 September 2021, Version of Record 27 September 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102734