@inproceedings{zhang-etal-2021-entity,
title = "Entity Relation Extraction as Dependency Parsing in Visually Rich Documents",
author = "Zhang, Yue and
Bo, Zhang and
Wang, Rui and
Cao, Junjie and
Li, Chen and
Bao, Zuyi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.218",
doi = "10.18653/v1/2021.emnlp-main.218",
pages = "2759--2768",
abstract = "Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e.,semantic entity), while the relations in-between are largely unexplored. In this paper, we adapt the popular dependency parsing model, the biaffine parser, to this entity relation extraction task. Being different from the original dependency parsing model which recognizes dependency relations between words, we identify relations between groups of words with layout information instead. We have compared different representations of the semantic entity, different VRD encoders, and different relation decoders. For the model training, we explore multi-task learning to combine entity labeling and relation extraction tasks; and for the evaluation, we conduct experiments on different datasets with filtering and augmentation. The results demonstrate that our proposed model achieves 65.96{\%} F1 score on the FUNSD dataset. As for the real-world application, our model has been applied to the in-house customs data, achieving reliable performance in the production setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-entity">
<titleInfo>
<title>Entity Relation Extraction as Dependency Parsing in Visually Rich Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Bo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuyi</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e.,semantic entity), while the relations in-between are largely unexplored. In this paper, we adapt the popular dependency parsing model, the biaffine parser, to this entity relation extraction task. Being different from the original dependency parsing model which recognizes dependency relations between words, we identify relations between groups of words with layout information instead. We have compared different representations of the semantic entity, different VRD encoders, and different relation decoders. For the model training, we explore multi-task learning to combine entity labeling and relation extraction tasks; and for the evaluation, we conduct experiments on different datasets with filtering and augmentation. The results demonstrate that our proposed model achieves 65.96% F1 score on the FUNSD dataset. As for the real-world application, our model has been applied to the in-house customs data, achieving reliable performance in the production setting.</abstract>
<identifier type="citekey">zhang-etal-2021-entity</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.218</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.218</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2759</start>
<end>2768</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Relation Extraction as Dependency Parsing in Visually Rich Documents
%A Zhang, Yue
%A Bo, Zhang
%A Wang, Rui
%A Cao, Junjie
%A Li, Chen
%A Bao, Zuyi
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F zhang-etal-2021-entity
%X Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e.,semantic entity), while the relations in-between are largely unexplored. In this paper, we adapt the popular dependency parsing model, the biaffine parser, to this entity relation extraction task. Being different from the original dependency parsing model which recognizes dependency relations between words, we identify relations between groups of words with layout information instead. We have compared different representations of the semantic entity, different VRD encoders, and different relation decoders. For the model training, we explore multi-task learning to combine entity labeling and relation extraction tasks; and for the evaluation, we conduct experiments on different datasets with filtering and augmentation. The results demonstrate that our proposed model achieves 65.96% F1 score on the FUNSD dataset. As for the real-world application, our model has been applied to the in-house customs data, achieving reliable performance in the production setting.
%R 10.18653/v1/2021.emnlp-main.218
%U https://aclanthology.org/2021.emnlp-main.218
%U https://doi.org/10.18653/v1/2021.emnlp-main.218
%P 2759-2768
Markdown (Informal)
[Entity Relation Extraction as Dependency Parsing in Visually Rich Documents](https://aclanthology.org/2021.emnlp-main.218) (Zhang et al., EMNLP 2021)
ACL