@inproceedings{ruoxi-etal-2024-dlue,
title = "{DLUE}: Benchmarking Document Language Understanding",
author = "Ruoxi, Xu and
Hongyu, Lin and
Xinyan, Guan and
Yingfei, Sun and
Le, Sun",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.97/",
pages = "1257--1269",
language = "eng",
abstract = "{\textquotedblleft}Understanding documents is central to many real-world tasks but remains a challenging topic.Unfortunately, there is no well-established consensus on how to comprehensively evaluate docu-ment understanding abilities, which significantly hinders the fair comparison and measuring theprogress of the field. To benchmark document understanding researches, this paper summarizesfour representative abilities, i.e., document classification, document structural analysis, docu-ment information extraction, and document transcription. Under the new evaluation framework,we propose Document Language Understanding Evaluation {--} DLUE, a new task suite whichcovers a wide-range of tasks in various forms, domains and document genres. We also systemat-ically evaluate six well-established transformer models and representative LLMs on DLUE, andfind that due to the lengthy content, complicated underlying structure and dispersed knowledge,document understanding is still far from being solved in complex real-world scenarios.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruoxi-etal-2024-dlue">
<titleInfo>
<title>DLUE: Benchmarking Document Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Ruoxi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Hongyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guan</namePart>
<namePart type="family">Xinyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Yingfei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Understanding documents is central to many real-world tasks but remains a challenging topic.Unfortunately, there is no well-established consensus on how to comprehensively evaluate docu-ment understanding abilities, which significantly hinders the fair comparison and measuring theprogress of the field. To benchmark document understanding researches, this paper summarizesfour representative abilities, i.e., document classification, document structural analysis, docu-ment information extraction, and document transcription. Under the new evaluation framework,we propose Document Language Understanding Evaluation – DLUE, a new task suite whichcovers a wide-range of tasks in various forms, domains and document genres. We also systemat-ically evaluate six well-established transformer models and representative LLMs on DLUE, andfind that due to the lengthy content, complicated underlying structure and dispersed knowledge,document understanding is still far from being solved in complex real-world scenarios.”</abstract>
<identifier type="citekey">ruoxi-etal-2024-dlue</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.97/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>1257</start>
<end>1269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DLUE: Benchmarking Document Language Understanding
%A Ruoxi, Xu
%A Hongyu, Lin
%A Xinyan, Guan
%A Yingfei, Sun
%A Le, Sun
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F ruoxi-etal-2024-dlue
%X “Understanding documents is central to many real-world tasks but remains a challenging topic.Unfortunately, there is no well-established consensus on how to comprehensively evaluate docu-ment understanding abilities, which significantly hinders the fair comparison and measuring theprogress of the field. To benchmark document understanding researches, this paper summarizesfour representative abilities, i.e., document classification, document structural analysis, docu-ment information extraction, and document transcription. Under the new evaluation framework,we propose Document Language Understanding Evaluation – DLUE, a new task suite whichcovers a wide-range of tasks in various forms, domains and document genres. We also systemat-ically evaluate six well-established transformer models and representative LLMs on DLUE, andfind that due to the lengthy content, complicated underlying structure and dispersed knowledge,document understanding is still far from being solved in complex real-world scenarios.”
%U https://aclanthology.org/2024.ccl-1.97/
%P 1257-1269
Markdown (Informal)
[DLUE: Benchmarking Document Language Understanding](https://aclanthology.org/2024.ccl-1.97/) (Ruoxi et al., CCL 2024)
ACL
- Xu Ruoxi, Lin Hongyu, Guan Xinyan, Sun Yingfei, and Sun Le. 2024. DLUE: Benchmarking Document Language Understanding. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 1257–1269, Taiyuan, China. Chinese Information Processing Society of China.