Synthesizing Scientific Summaries: An Extractive and Abstractive Approach

TL;DR

This paper presents a hybrid extractive-abstractive approach to scientific paper summarisation, leveraging unsupervised extraction models and transformer-based summarisation to improve key information capture and potentially surpass human summaries.

Contribution

The paper introduces a novel hybrid methodology combining extractive and abstractive techniques for scientific paper summarisation, evaluated with multiple models and metrics.

Findings

Certain hyperparameter combinations enable summaries to be more abstract than human-written ones.

The hybrid approach effectively captures key research findings and motivations.

Model performance exceeds some benchmarks in summarisation quality.

Abstract

The availability of a vast array of research papers in any area of study, necessitates the need of automated summarisation systems that can present the key research conducted and their corresponding findings. Scientific paper summarisation is a challenging task for various reasons including token length limits in modern transformer models and corresponding memory and compute requirements for long text. A significant amount of work has been conducted in this area, with approaches that modify the attention mechanisms of existing transformer models and others that utilise discourse information to capture long range dependencies in research papers. In this paper, we propose a hybrid methodology for research paper summarisation which incorporates an extractive and abstractive approach. We use the extractive approach to capture the key findings of research, and pair it with the introduction of the paper which captures the motivation for research. We use two models based on unsupervised learning for the extraction stage and two transformer language models, resulting in four combinations for our hybrid approach. The performances of the models are evaluated on three metrics and we present our findings in this paper. We find that using certain combinations of hyper parameters, it is possible for automated summarisation systems to exceed the abstractiveness of summaries written by humans. Finally, we state our future scope of research in extending this methodology to summarisation of generalised long documents.