A non-factoid question answering system for prior art search

作者：

Highlights：

• Bidirectional embedding has impactful contributions to meaningful answer discovery.

• Topic modeling is critical in diversified answer discovery during prior art search.

• Provides a reliable framework to prior art search.

• Experiments on real datasets demonstrate the effectiveness of the framework.

摘要

•Bidirectional embedding has impactful contributions to meaningful answer discovery.•Topic modeling is critical in diversified answer discovery during prior art search.•Provides a reliable framework to prior art search.•Experiments on real datasets demonstrate the effectiveness of the framework.

论文关键词：Question answering,Prior art search,Pre-trained embeddings,Topic modeling,Search diversification,Sensemaking

论文评审过程：Received 25 May 2020, Revised 16 August 2020, Accepted 10 March 2021, Available online 18 March 2021, Version of Record 10 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114910