ATLAS: Improving Lay Summarisation with Attribute-based Control

TL;DR

ATLAS introduces an attribute-based control method for abstractive lay summarisation, enabling tailored summaries for diverse audiences and outperforming existing models on biomedical datasets.

Contribution

The paper presents a novel controllable summarisation model that adjusts content and style attributes to produce more accessible scientific summaries.

Findings

ATLAS outperforms state-of-the-art baselines on biomedical datasets.

Controlled attributes influence the 'layness' of summaries effectively.

Analyses show the attributes' discriminatory power and emergent influence.

Abstract

Lay summarisation aims to produce summaries of scientific articles that are comprehensible to non-expert audiences. However, previous work assumes a one-size-fits-all approach, where the content and style of the produced summary are entirely dependent on the data used to train the model. In practice, audiences with different levels of expertise will have specific needs, impacting what content should appear in a lay summary and how it should be presented. Aiming to address this, we propose ATLAS, a novel abstractive summarisation approach that can control various properties that contribute to the overall "layness" of the generated summary using targeted control attributes. We evaluate ATLAS on a combination of biomedical lay summarisation datasets, where it outperforms state-of-the-art baselines using mainstream summarisation metrics. Additional analyses provided on the discriminatory power and emergent influence of our selected controllable attributes further attest to the effectiveness of our approach.