Comparison of automatic summarisation methods for clinical free text notes
作者：
Highlights：
• Eight automatic text summarisation methods are described and tested.
• Word space models of distributional semantics are used in five of the presented methods.
• A composition based summarisation method outperforms the other considered methods.
• The utilised automatic evaluation approach is shown to correlate with manual evaluation.
摘要
Highlights•Eight automatic text summarisation methods are described and tested.•Word space models of distributional semantics are used in five of the presented methods.•A composition based summarisation method outperforms the other considered methods.•The utilised automatic evaluation approach is shown to correlate with manual evaluation.
论文关键词：Automatic text summarisation,Summarisation evaluation,Distributional semantics,Word space models,Clinical text processing,Electronic health records
论文评审过程：Received 4 May 2015, Revised 14 December 2015, Accepted 5 January 2016, Available online 21 January 2016, Version of Record 15 March 2016.
论文官网地址：https://doi.org/10.1016/j.artmed.2016.01.003
