What's New? Summarizing Contributions in Scientific Literature

11/06/2020
by   Hiroaki Hayashi, et al.
0

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 considered more helpful than traditional scientific paper summarization.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/19/2019

Structured Summarization of Academic Publications

We propose SUSIE, a novel summarization method that can work with state-...
10/01/2019

BillSum: A Corpus for Automatic Summarization of US Legislation

Automatic summarization methods have been studied on a variety of domain...
10/19/2020

Dimsum @LaySumm 20: BART-based Approach for Scientific Document Summarization

Lay summarization aims to generate lay summaries of scientific papers au...
05/23/2017

Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge

Citation texts are sometimes not very informative or in some cases inacc...
04/30/2020

TLDR: Extreme Summarization of Scientific Documents

We introduce TLDR generation for scientific papers, a new automatic summ...
12/07/2021

Change Summarization of Diachronic Scholarly Paper Collections by Semantic Evolution Analysis

The amount of scholarly data has been increasing dramatically over the l...
08/22/2022

Contributions à l'asservissement visuel et à l'imagerie en médecine

This manuscript gives an overview of my research work carried out within...