Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data
This work addresses the need for automated summarization of biomedical data, but it is incremental as it builds on existing methods and datasets like BioASQ.
The paper tackled the problem of extracting multi-document summaries for queries in biomedical publications by comparing supervised machine learning approaches, showing that a simple annotation method for classification outperforms regression-based summarization.
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.