Sequence-Based Extractive Summarisation for Scientific Articles

TL;DR

This paper investigates supervised extractive summarisation of scientific articles using a sequential tagging model, demonstrating its effectiveness and potential for discipline-specific adaptation with minimal feature enhancements.

Contribution

It introduces a simple sequential tagging approach for scientific article summarisation and analyzes its performance across different academic disciplines.

Findings

Sequential model achieves high summarisation accuracy.

Additional sentence features provide minimal improvements.

Discipline-specific structure influences model effectiveness.

Abstract

This paper presents the results of research on supervised extractive text summarisation for scientific articles. We show that a simple sequential tagging model based only on the text within a document achieves high results against a simple classification model. Improvements can be achieved through additional sentence-level features, though these were minimal. Through further analysis, we show the potential of the sequential model relying on the structure of the document depending on the academic discipline which the document is from.