What's new? Summarizing Contributions in Scientific LiteratureDownload PDF

28 Sept 2020 (modified: 22 Oct 2023)ICLR 2021 Conference Blind SubmissionReaders: Everyone
Keywords: abstractive summarization, scientific papers
Abstract: With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome this problem, we introduce a new task of $\textit{disentangled paper summarization}$, which seeks to generate separate summaries for the paper contributions and the context of the work, making it easier to identify the key findings shared in articles. For this purpose, we extend the S2ORC corpus of academic articles, which spans a diverse set of domains ranging from economics to psychology, by adding disentangled "contribution" and "context" reference labels. Together with the dataset, we introduce and analyze three baseline approaches: 1) a unified model controlled by input code prefixes, 2) a model with separate generation heads specialized in generating the disentangled outputs, and 3) a training strategy that guides the model using additional supervision coming from inbound and outbound citations. We also propose a comprehensive automatic evaluation protocol which reports the $\textit{relevance}$, $\textit{novelty}$, and $\textit{disentanglement}$ of generated outputs. Through a human study involving expert annotators, we show that in 79%, of cases our new task is considered more helpful than traditional scientific paper summarization.
One-sentence Summary: We propose a new task of disentangled paper summarization which aims to summarize contributions and contexts of scientific papers, we show the importance and usefulness of the task through experiments.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2011.03161/code)
Reviewed Version (pdf): https://openreview.net/references/pdf?id=dqVButG8OK
12 Replies

Loading