Neural Abstractive Summarization for Long Text and Multiple Tables

Shuaiqi Liu, Jiannong Cao, Zhongfen Deng, Wenting Zhao, Ruosong Yang, Zhiyuan Wen, Philip S. Yu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Abstractive summarization aims to generate a concise summary covering the input document's salient information. Within a report document, the salient information can be scattered in the textual and non-textual content. However, existing document summarization datasets and methods usually focus on the text and filter out the non-textual content. Missing tabular data can limit produced summaries’ informativeness, especially when summaries require covering quantitative descriptions of critical metrics in tables. Existing datasets and methods cannot meet the requirements of summarizing long text and dozens of tables in each report document. To deal with the scarcity of available datasets, we propose FINDSum, the first large-scale dataset for long text and multi-table summarization. Built on 21,125 annual reports from 3,794 companies, FINDSum has two subsets for summarizing each company's results of operations and liquidity. Besides, we present four types of summarization methods to jointly consider text and table content when summarizing reports. Additionally, we propose a set of evaluation metrics to assess the usage of numerical information in produced summaries. Our summarization methods significantly outperform advanced baselines, which verifies the necessity of incorporating textual and tabular data when summarizing report documents. We also conduct extensive comparative experiments to identify vital model components and configurations that can improve summarization results.
Original languageEnglish
Pages (from-to)2572 - 2586
Number of pages15
JournalIEEE Transactions on Knowledge and Data Engineering
Volume36
Issue number6
DOIs
Publication statusPublished - 1 Jun 2024

Keywords

  • Document summarization
  • natural language generation
  • natural language processing
  • text summarization

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Neural Abstractive Summarization for Long Text and Multiple Tables'. Together they form a unique fingerprint.

Cite this