What's New? Summarizing Contributions in Scientific Literature
Authors:
- Hiroaki HayashiHHHiroaki Hayashi
- Wojciech KryścińskiWKWojciech Kryściński
- Bryan McCannBMBryan McCann
- Nazneen RajaniNRNazneen Rajani
- Caiming XiongCXCaiming Xiong
Preprint
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 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 relevance, novelty, and 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.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- S2ORC: The Semantic Scholar Open Research Corpus2020
- ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Text Summarization with Pretrained Encoders2019
- SciBERT: A Pretrained Language Model for Scientific Text2019
- A Temporally Sensitive Submodularity Framework for Timeline Summarization2018
- A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents2018
- A Supervised Approach to Extractive Summarisation of Scientific Papers2017
- Scientific Article Summarization Using Citation-Context and Article's Discourse Structure2015
- Nouveau-ROUGE: A Novelty Metric for Update SummarizationComputational Linguistics, 2011