@inproceedings{liu-etal-2022-long,
title = "Long Text and Multi-Table Summarization: Dataset and Method",
author = "Liu, Shuaiqi and
Cao, Jiannong and
Yang, Ruosong and
Wen, Zhiyuan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.145/",
doi = "10.18653/v1/2022.findings-emnlp.145",
pages = "1995--2010",
abstract = "Automatic document summarization aims to produce 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 multiple tables in each report. To deal with the scarcity of available data, 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, it has two subsets for summarizing each company`s results of operations and liquidity. To summarize the long text and dozens of tables in each report, we present three types of summarization methods. Besides, we propose a set of evaluation metrics to assess the usage of numerical information in produced summaries. Dataset analyses and experimental results indicate the importance of jointly considering input textual and tabular data when summarizing report documents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-long">
<titleInfo>
<title>Long Text and Multi-Table Summarization: Dataset and Method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuaiqi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiannong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic document summarization aims to produce 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 multiple tables in each report. To deal with the scarcity of available data, 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, it has two subsets for summarizing each company‘s results of operations and liquidity. To summarize the long text and dozens of tables in each report, we present three types of summarization methods. Besides, we propose a set of evaluation metrics to assess the usage of numerical information in produced summaries. Dataset analyses and experimental results indicate the importance of jointly considering input textual and tabular data when summarizing report documents.</abstract>
<identifier type="citekey">liu-etal-2022-long</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.145</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.145/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1995</start>
<end>2010</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Long Text and Multi-Table Summarization: Dataset and Method
%A Liu, Shuaiqi
%A Cao, Jiannong
%A Yang, Ruosong
%A Wen, Zhiyuan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F liu-etal-2022-long
%X Automatic document summarization aims to produce 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 multiple tables in each report. To deal with the scarcity of available data, 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, it has two subsets for summarizing each company‘s results of operations and liquidity. To summarize the long text and dozens of tables in each report, we present three types of summarization methods. Besides, we propose a set of evaluation metrics to assess the usage of numerical information in produced summaries. Dataset analyses and experimental results indicate the importance of jointly considering input textual and tabular data when summarizing report documents.
%R 10.18653/v1/2022.findings-emnlp.145
%U https://aclanthology.org/2022.findings-emnlp.145/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.145
%P 1995-2010
Markdown (Informal)
[Long Text and Multi-Table Summarization: Dataset and Method](https://aclanthology.org/2022.findings-emnlp.145/) (Liu et al., Findings 2022)
ACL