Challenge: Lay summarisation aims to produce scientific summaries that are comprehensible to non-experts.
Approach: They propose an abstractive summarisation approach that can control properties contributing to overall "layness" they evaluate ATLAS on a combination of biomedical lay summarization datasets.
Outcome: The proposed approach outperforms state-of-the-art summarisation metrics on biomedical datasets and shows that it can be discriminatory and emergently influenced.

Similar Papers

Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects - A Survey (2024.findings-acl)

Copied to clipboard

Challenge: scholarly attention has turned to the development of text summarization methods that are more closely tailored and controlled to align with specific objectives and user needs.
Approach: They formalize a controllable text summarization task and categorize controllability attributes according to their shared characteristics and objectives.
Outcome: The proposed method is tailored to meet the specific intent and needs of users.
Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature (2022.emnlp-main)

Copied to clipboard

Challenge: Existing datasets for lay summarisation are limited in size and scope, hindering the development of data-driven approaches.
Approach: They propose to use two new datasets for the lay summarisation of biomedical research articles to characterise their lay summaries.
Outcome: The proposed datasets are compared with existing datasets and show they can be leveraged to support different audiences and applications.
Fact-based Content Weighting for Evaluating Abstractive Summarisation (2020.acl-main)

Copied to clipboard

Challenge: Abstractive summarisation is notoriously hard to evaluate since word-overlap-based metrics are insufficient.
Approach: They propose a new evaluation metric which is based on fact-level content weighting, relating the facts of the document to the facts in the summary.
Outcome: The proposed evaluation metric is highly correlated to human perception and compares favourably to the recent manual highlight-based metric of Hardy et al.
Readability Controllable Biomedical Document Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing controllable summarization systems for biomedical documents have little attention to readability control, leaving users with incompatible summaries .
Approach: They propose a task of readability controllable summarization for biomedical documents to generate summaries that are incompatible with users' levels of expertise.
Outcome: The proposed model is based on pre-trained language models with prevalent controlling and generation techniques and evaluates the readability discrepancy between lay and technical summaries.
Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on aspect-based abstractive summarization assume a small set of aspects and do not consider other diverse aspects.
Approach: They propose a weak supervision construction method and an aspect modeling scheme to solve this problem.
Outcome: The proposed method significantly expands the application of the task in practice.
Understanding LLMs’ summarization capabilities: an analysis of biomedical abstract and lay summary generation (2026.findings-acl)

Copied to clipboard

Challenge: Abstracts use technical language for academic audiences, while lay summaries aim to make findings accessible to non-specialists.
Approach: They evaluate the performance of lightweight LLMs in generating biomedical abstracts and lay summaries in a zero-shot setting.
Outcome: The proposed models perform well in generating biomedical abstracts and lay summaries in a zero-shot setting.
SumPubMed: Summarization Dataset of PubMed Scientific Articles (2021.acl-srw)

Copied to clipboard

Challenge: Existing summarization models that can extract the top few lines of news articles fail to summarize long documents.
Approach: They constructed a scientific summarization dataset from MEDLINE articles from the PubMed archive to address this problem.
Outcome: The proposed model outperforms existing models on news article summarization datasets and shows that it is more efficient to extract the top few lines.
CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability (2023.emnlp-demo)

Copied to clipboard

Challenge: Using a controlled summarization system, we provide a toolkit for scientific summarizing documents.
Approach: They propose a toolkit for controlled summarization of scientific documents that adjusts key attributes specifically of length and keyword inclusion.
Outcome: The proposed system generates high-quality summaries based on user preferences, adjusting key attributes specifically of length and keyword inclusion.
Effective Crowdsourcing for a New Type of Summarization Task (N18-2)

Copied to clipboard

Challenge: Currently, summarization research focuses on summarizing the entire text, but in practice, readers are often interested in only one aspect of the document or conversation.
Approach: They propose a new task where the goal is to summarize a particular aspect of a document.
Outcome: The proposed task is based on a crowdsourced data collection workflow that allows users to collect high-quality summaries.
Aspect-Controllable Opinion Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work on opinion summarization produces general summaries based on reviews and popularity of opinions expressed in them.
Approach: They propose an approach that generates customized opinion summaries based on aspect queries.
Outcome: The proposed model outperforms the current state of the art and generates personalized summaries by controlling the number of aspects discussed in them.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations