@inproceedings{shaojie-etal-2023-document,
title = "Document Information Extraction via Global Tagging",
author = "He, Shaojie and
Wang, Tianshu and
Lu, Yaojie and
Lin, Hongyu and
Han, Xianpei and
Sun, Yingfei and
Sun, Le",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.62/",
pages = "726--735",
language = "eng",
abstract = "``Document Information Extraction (DIE) is a crucial task for extracting key information fromvisually-rich documents. The typical pipeline approach for this task involves Optical Charac-ter Recognition (OCR), serializer, Semantic Entity Recognition (SER), and Relation Extraction(RE) modules. However, this pipeline presents significant challenges in real-world scenariosdue to issues such as unnatural text order and error propagation between different modules. Toaddress these challenges, we propose a novel tagging-based method {--} Global TaggeR (GTR),which converts the original sequence labeling task into a token relation classification task. Thisapproach globally links discontinuous semantic entities in complex layouts, and jointly extractsentities and relations from documents. In addition, we design a joint training loss and a jointdecoding strategy for SER and RE tasks based on GTR. Our experiments on multiple datasetsdemonstrate that GTR not only mitigates the issue of text in the wrong order but also improvesRE performance. Introduction''"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shaojie-etal-2023-document">
<titleInfo>
<title>Document Information Extraction via Global Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaojie</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianshu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaojie</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingfei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Chinese National Conference on Computational Linguistics</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">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</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>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Document Information Extraction (DIE) is a crucial task for extracting key information fromvisually-rich documents. The typical pipeline approach for this task involves Optical Charac-ter Recognition (OCR), serializer, Semantic Entity Recognition (SER), and Relation Extraction(RE) modules. However, this pipeline presents significant challenges in real-world scenariosdue to issues such as unnatural text order and error propagation between different modules. Toaddress these challenges, we propose a novel tagging-based method – Global TaggeR (GTR),which converts the original sequence labeling task into a token relation classification task. Thisapproach globally links discontinuous semantic entities in complex layouts, and jointly extractsentities and relations from documents. In addition, we design a joint training loss and a jointdecoding strategy for SER and RE tasks based on GTR. Our experiments on multiple datasetsdemonstrate that GTR not only mitigates the issue of text in the wrong order but also improvesRE performance. Introduction”</abstract>
<identifier type="citekey">shaojie-etal-2023-document</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.62/</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>726</start>
<end>735</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Information Extraction via Global Tagging
%A He, Shaojie
%A Wang, Tianshu
%A Lu, Yaojie
%A Lin, Hongyu
%A Han, Xianpei
%A Sun, Yingfei
%A Sun, Le
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G eng
%F shaojie-etal-2023-document
%X “Document Information Extraction (DIE) is a crucial task for extracting key information fromvisually-rich documents. The typical pipeline approach for this task involves Optical Charac-ter Recognition (OCR), serializer, Semantic Entity Recognition (SER), and Relation Extraction(RE) modules. However, this pipeline presents significant challenges in real-world scenariosdue to issues such as unnatural text order and error propagation between different modules. Toaddress these challenges, we propose a novel tagging-based method – Global TaggeR (GTR),which converts the original sequence labeling task into a token relation classification task. Thisapproach globally links discontinuous semantic entities in complex layouts, and jointly extractsentities and relations from documents. In addition, we design a joint training loss and a jointdecoding strategy for SER and RE tasks based on GTR. Our experiments on multiple datasetsdemonstrate that GTR not only mitigates the issue of text in the wrong order but also improvesRE performance. Introduction”
%U https://aclanthology.org/2023.ccl-1.62/
%P 726-735
Markdown (Informal)
[Document Information Extraction via Global Tagging](https://aclanthology.org/2023.ccl-1.62/) (He et al., CCL 2023)
ACL
- Shaojie He, Tianshu Wang, Yaojie Lu, Hongyu Lin, Xianpei Han, Yingfei Sun, and Le Sun. 2023. Document Information Extraction via Global Tagging. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 726–735, Harbin, China. Chinese Information Processing Society of China.