LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding

Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for m...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-09
Main Authors: Xu, Yiheng, Lv, Tengchao, Cui, Lei, Wang, Guoxin, Lu, Yijuan, Dinei Florencio, Zhang, Cha, Furu Wei
Format: Article
Language:English
Subjects:
Datasets
Multilingualism
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Xu, Yiheng
Lv, Tengchao
Cui, Lei
Wang, Guoxin
Lu, Yijuan
Dinei Florencio
Zhang, Cha
Furu Wei
description Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The pre-trained LayoutXLM model and the XFUND dataset are publicly available at https://aka.ms/layoutxlm.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2515486371</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2515486371</sourcerecordid><originalsourceid>FETCH-proquest_journals_25154863713</originalsourceid><addsrcrecordid>eNqNik0LgjAAQEcQJOV_GHQe6OZUuvZBB4UOFd5k6KzJ3GofB_99g_oBnR6P9xYgwoSkqMwwXoHY2jFJEpwXmFISgaZis_auqeodrL10YtI9k_BiOHKGCSXUAw7afJsM5kO9CxsgZ2RE94QH3fmJKwdvqufGOqb68G3AcmDS8vjHNdiejtf9Gb2MfntuXTtqb1RILaYpzcqcFCn57_oA1gVCgQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2515486371</pqid></control><display><type>article</type><title>LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding</title><source>Publicly Available Content Database</source><creator>Xu, Yiheng ; Lv, Tengchao ; Cui, Lei ; Wang, Guoxin ; Lu, Yijuan ; Dinei Florencio ; Zhang, Cha ; Furu Wei</creator><creatorcontrib>Xu, Yiheng ; Lv, Tengchao ; Cui, Lei ; Wang, Guoxin ; Lu, Yijuan ; Dinei Florencio ; Zhang, Cha ; Furu Wei</creatorcontrib><description>Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The pre-trained LayoutXLM model and the XFUND dataset are publicly available at https://aka.ms/layoutxlm.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Datasets ; Multilingualism ; Training</subject><ispartof>arXiv.org, 2021-09</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2515486371?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25751,37010,44588</link.rule.ids></links><search><creatorcontrib>Xu, Yiheng</creatorcontrib><creatorcontrib>Lv, Tengchao</creatorcontrib><creatorcontrib>Cui, Lei</creatorcontrib><creatorcontrib>Wang, Guoxin</creatorcontrib><creatorcontrib>Lu, Yijuan</creatorcontrib><creatorcontrib>Dinei Florencio</creatorcontrib><creatorcontrib>Zhang, Cha</creatorcontrib><creatorcontrib>Furu Wei</creatorcontrib><title>LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding</title><title>arXiv.org</title><description>Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The pre-trained LayoutXLM model and the XFUND dataset are publicly available at https://aka.ms/layoutxlm.</description><subject>Datasets</subject><subject>Multilingualism</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNik0LgjAAQEcQJOV_GHQe6OZUuvZBB4UOFd5k6KzJ3GofB_99g_oBnR6P9xYgwoSkqMwwXoHY2jFJEpwXmFISgaZis_auqeodrL10YtI9k_BiOHKGCSXUAw7afJsM5kO9CxsgZ2RE94QH3fmJKwdvqufGOqb68G3AcmDS8vjHNdiejtf9Gb2MfntuXTtqb1RILaYpzcqcFCn57_oA1gVCgQ</recordid><startdate>20210909</startdate><enddate>20210909</enddate><creator>Xu, Yiheng</creator><creator>Lv, Tengchao</creator><creator>Cui, Lei</creator><creator>Wang, Guoxin</creator><creator>Lu, Yijuan</creator><creator>Dinei Florencio</creator><creator>Zhang, Cha</creator><creator>Furu Wei</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210909</creationdate><title>LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding</title><author>Xu, Yiheng ; Lv, Tengchao ; Cui, Lei ; Wang, Guoxin ; Lu, Yijuan ; Dinei Florencio ; Zhang, Cha ; Furu Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25154863713</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Datasets</topic><topic>Multilingualism</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Xu, Yiheng</creatorcontrib><creatorcontrib>Lv, Tengchao</creatorcontrib><creatorcontrib>Cui, Lei</creatorcontrib><creatorcontrib>Wang, Guoxin</creatorcontrib><creatorcontrib>Lu, Yijuan</creatorcontrib><creatorcontrib>Dinei Florencio</creatorcontrib><creatorcontrib>Zhang, Cha</creatorcontrib><creatorcontrib>Furu Wei</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xu, Yiheng</au><au>Lv, Tengchao</au><au>Cui, Lei</au><au>Wang, Guoxin</au><au>Lu, Yijuan</au><au>Dinei Florencio</au><au>Zhang, Cha</au><au>Furu Wei</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding</atitle><jtitle>arXiv.org</jtitle><date>2021-09-09</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The pre-trained LayoutXLM model and the XFUND dataset are publicly available at https://aka.ms/layoutxlm.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2515486371
source Publicly Available Content Database
subjects Datasets
Multilingualism
Training
title LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T11%3A34%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=LayoutXLM:%20Multimodal%20Pre-training%20for%20Multilingual%20Visually-rich%20Document%20Understanding&rft.jtitle=arXiv.org&rft.au=Xu,%20Yiheng&rft.date=2021-09-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2515486371%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_25154863713%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2515486371&rft_id=info:pmid/&rfr_iscdi=true