@inproceedings{dong-etal-2023-lightweight,
title = "Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents",
author = "Dong, Yanfei and
Deng, Lambert and
Zhang, Jiazheng and
Yu, Xiaodong and
Lin, Ting and
Gelli, Francesco and
Poria, Soujanya and
Lee, Wee Sun",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.108",
doi = "10.18653/v1/2023.findings-eacl.108",
pages = "1471--1484",
abstract = "Documents that consist of diverse templates and exhibit complex spatial structures pose a challenge for document entity classification. We propose KNN-Former, which incorporates a new kind of spatial bias in attention calculation based on the K-nearest-neighbor (KNN) graph of document entities. We limit entities{'} attention only to their local radius defined by the KNN graph. We also use combinatorial matching to address the one-to-one mapping property that exists in many documents, where one field has only one corresponding entity. Moreover, our method is highly parameter-efficient compared to existing approaches in terms of the number of trainable parameters. Despite this, experiments across various datasets show our method outperforms baselines in most entity types. Many real-world documents exhibit combinatorial properties which can be leveraged as inductive biases to improve extraction accuracy, but existing datasets do not cover these documents. To facilitate future research into these types of documents, we release a new ID document dataset that covers diverse templates and languages. We also release enhanced annotations for an existing dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2023-lightweight">
<titleInfo>
<title>Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanfei</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lambert</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiazheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Gelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wee</namePart>
<namePart type="given">Sun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Documents that consist of diverse templates and exhibit complex spatial structures pose a challenge for document entity classification. We propose KNN-Former, which incorporates a new kind of spatial bias in attention calculation based on the K-nearest-neighbor (KNN) graph of document entities. We limit entities’ attention only to their local radius defined by the KNN graph. We also use combinatorial matching to address the one-to-one mapping property that exists in many documents, where one field has only one corresponding entity. Moreover, our method is highly parameter-efficient compared to existing approaches in terms of the number of trainable parameters. Despite this, experiments across various datasets show our method outperforms baselines in most entity types. Many real-world documents exhibit combinatorial properties which can be leveraged as inductive biases to improve extraction accuracy, but existing datasets do not cover these documents. To facilitate future research into these types of documents, we release a new ID document dataset that covers diverse templates and languages. We also release enhanced annotations for an existing dataset.</abstract>
<identifier type="citekey">dong-etal-2023-lightweight</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.108</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.108</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1471</start>
<end>1484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents
%A Dong, Yanfei
%A Deng, Lambert
%A Zhang, Jiazheng
%A Yu, Xiaodong
%A Lin, Ting
%A Gelli, Francesco
%A Poria, Soujanya
%A Lee, Wee Sun
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F dong-etal-2023-lightweight
%X Documents that consist of diverse templates and exhibit complex spatial structures pose a challenge for document entity classification. We propose KNN-Former, which incorporates a new kind of spatial bias in attention calculation based on the K-nearest-neighbor (KNN) graph of document entities. We limit entities’ attention only to their local radius defined by the KNN graph. We also use combinatorial matching to address the one-to-one mapping property that exists in many documents, where one field has only one corresponding entity. Moreover, our method is highly parameter-efficient compared to existing approaches in terms of the number of trainable parameters. Despite this, experiments across various datasets show our method outperforms baselines in most entity types. Many real-world documents exhibit combinatorial properties which can be leveraged as inductive biases to improve extraction accuracy, but existing datasets do not cover these documents. To facilitate future research into these types of documents, we release a new ID document dataset that covers diverse templates and languages. We also release enhanced annotations for an existing dataset.
%R 10.18653/v1/2023.findings-eacl.108
%U https://aclanthology.org/2023.findings-eacl.108
%U https://doi.org/10.18653/v1/2023.findings-eacl.108
%P 1471-1484
Markdown (Informal)
[Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents](https://aclanthology.org/2023.findings-eacl.108) (Dong et al., Findings 2023)
ACL
- Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, and Wee Sun Lee. 2023. Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1471–1484, Dubrovnik, Croatia. Association for Computational Linguistics.