{"id":"https://openalex.org/W3035089734","doi":"https://doi.org/10.1145/3397271.3401442","title":"Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models","display_name":"Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3035089734","doi":"https://doi.org/10.1145/3397271.3401442","mag":"3035089734"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103141505","display_name":"Mengxi Wei","orcid":"https://orcid.org/0000-0003-3588-0880"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxi Wei","raw_affiliation_strings":["Alibaba Group, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585745","display_name":"Yifan He","orcid":"https://orcid.org/0000-0002-9171-3502"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"YIfan He","raw_affiliation_strings":["Alibaba Group, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407302","display_name":"Qiong Zhang","orcid":"https://orcid.org/0000-0003-3617-3221"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiong Zhang","raw_affiliation_strings":["Alibaba Group, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2367","last_page":"2376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8809767961502075},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5996893644332886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.565474271774292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5654430985450745},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5622018575668335},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5333948731422424},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49389129877090454},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4753653407096863},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.451852023601532},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43591511249542236},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12822380661964417},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.0855652391910553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8809767961502075},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5996893644332886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565474271774292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5654430985450745},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5622018575668335},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5333948731422424},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49389129877090454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4753653407096863},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.451852023601532},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43591511249542236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12822380661964417},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0855652391910553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1541720361","https://openalex.org/W2115733720","https://openalex.org/W2131774270","https://openalex.org/W2133774033","https://openalex.org/W2144962591","https://openalex.org/W2194775991","https://openalex.org/W2600702321","https://openalex.org/W2747329762","https://openalex.org/W2811000613","https://openalex.org/W2922714365","https://openalex.org/W2930925340","https://openalex.org/W2931198394","https://openalex.org/W2949212908","https://openalex.org/W2951216772","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963341924","https://openalex.org/W2964316912","https://openalex.org/W2971048662","https://openalex.org/W2971258845","https://openalex.org/W2995025784","https://openalex.org/W4299637834"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2039176012"],"abstract_inverted_index":{"Many":[0],"business":[1,70],"documents":[2,42],"processed":[3],"in":[4,13,69],"modern":[5],"NLP":[6],"and":[7,30,44,57,66],"IR":[8],"pipelines":[9],"are":[10],"visually":[11,40],"rich:":[12],"addition":[14],"to":[15,61,78,83],"text,":[16],"their":[17],"semantics":[18],"can":[19],"also":[20],"be":[21],"captured":[22],"by":[23],"visual":[24,67],"traits":[25],"such":[26],"as":[27],"layout,":[28],"format,":[29],"fonts.":[31],"We":[32,72],"study":[33],"the":[34,50],"problem":[35],"of":[36,52,88],"information":[37,68],"extraction":[38],"from":[39],"rich":[41],"(VRDs)":[43],"present":[45],"a":[46],"model":[47],"that":[48],"combines":[49],"power":[51],"large":[53,86],"pre-trained":[54],"language":[55],"models":[56],"graph":[58],"neural":[59],"networks":[60],"efficiently":[62],"encode":[63],"both":[64],"textual":[65],"documents.":[71],"further":[73],"introduce":[74],"new":[75],"fine-tuning":[76,82],"objectives":[77],"improve":[79],"in-domain":[80,90],"unsupervised":[81],"better":[84],"utilize":[85],"amount":[87],"unlabeled":[89],"data.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}