Generating a Structured Summary of Numerous Academic Papers: Dataset and Method

TL;DR

This paper introduces BigSurvey, a large-scale dataset for multi-document summarization of academic papers, and proposes CAST, a novel method that effectively generates structured summaries from numerous input documents.

Contribution

The paper presents BigSurvey, the first large-scale dataset for academic multi-document summarization, and introduces CAST, a new method for efficient, structured summarization of many papers.

Findings

CAST outperforms existing summarization methods

BigSurvey enables comprehensive academic paper summarization

Efficient processing of long texts achieved

Abstract

Writing a survey paper on one research topic usually needs to cover the salient content from numerous related papers, which can be modeled as a multi-document summarization (MDS) task. Existing MDS datasets usually focus on producing the structureless summary covering a few input documents. Meanwhile, previous structured summary generation works focus on summarizing a single document into a multi-section summary. These existing datasets and methods cannot meet the requirements of summarizing numerous academic papers into a structured summary. To deal with the scarcity of available data, we propose BigSurvey, the first large-scale dataset for generating comprehensive summaries of numerous academic papers on each topic. We collect target summaries from more than seven thousand survey papers and utilize their 430 thousand reference papers' abstracts as input documents. To organize the diverse content from dozens of input documents and ensure the efficiency of processing long text sequences, we propose a summarization method named category-based alignment and sparse transformer (CAST). The experimental results show that our CAST method outperforms various advanced summarization methods.