Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data

TL;DR

This paper evaluates supervised machine learning methods for extractive query-based summarisation of biomedical literature, finding that classification approaches outperform regression methods in this context.

Contribution

It introduces a simple annotation approach for training classifiers and demonstrates its effectiveness over regression-based methods for biomedical summarisation.

Findings

Classification methods outperform regression in summarisation tasks.

A simple annotation approach improves training effectiveness.

The study uses BioASQ Challenge data for evaluation.

Abstract

The automation of text summarisation of biomedical publications is a pressing need due to the plethora of information available on-line. This paper explores the impact of several supervised machine learning approaches for extracting multi-document summaries for given queries. In particular, we compare classification and regression approaches for query-based extractive summarisation using data provided by the BioASQ Challenge. We tackled the problem of annotating sentences for training classification systems and show that a simple annotation approach outperforms regression-based summarisation.