Different approaches for identifying important concepts in probabilistic biomedical text summarization

Milad Moradi, Nasser Ghadiri

Abstract: Highlights•Introducing a Bayesian summarizer for biomedical text documents.•Different feature selection approaches for identifying important concepts in a biomedical text.•The efficiency of feature selection methods are evaluated on the performance of the Bayesian text summarizer.•The distribution of important concepts is used to classify the sentences of an input document.•The summarizer outperforms other frequency-based, domain-independent and baseline methods.