SemBioNLQA: A semantic biomedical question answering system for retrieving exact and ideal answers to natural language questions

Highlights：

• A new semantic biomedical question answering system named SemBioNLQA for retrieving exact and ideal answers to natural language questions is presented.

• SemBioNLQA, a fully automatic system, integrates NLP methods in question classification, document retrieval, passage retrieval and answer extraction modules.

• It is able to accept a variety of natural language questions and to generate appropriate natural language answers.

• Experimental evaluations performed on biomedical questions provided by the BioASQ challenge show that SemBioNLQA achieves good performances compared with the current state-of-the-art systems.

• The SemBioNLQA source code is available at https://github.com/sarrouti/sembionlqa.

摘要

•A new semantic biomedical question answering system named SemBioNLQA for retrieving exact and ideal answers to natural language questions is presented.•SemBioNLQA, a fully automatic system, integrates NLP methods in question classification, document retrieval, passage retrieval and answer extraction modules.•It is able to accept a variety of natural language questions and to generate appropriate natural language answers.•Experimental evaluations performed on biomedical questions provided by the BioASQ challenge show that SemBioNLQA achieves good performances compared with the current state-of-the-art systems.•The SemBioNLQA source code is available at https://github.com/sarrouti/sembionlqa.

论文关键词：Biomedical question answering,Information retrieval,Passage retrieval,Natural language processing,Machine learning,Biomedical informatics,BioASQ

论文评审过程：Received 4 May 2018, Revised 19 November 2019, Accepted 19 November 2019, Available online 28 November 2019, Version of Record 6 December 2019.