{"id":"https://openalex.org/W3137695810","doi":"https://doi.org/10.14778/3446095.3446104","title":"Improving information extraction from visually rich documents using visual span representations","display_name":"Improving information extraction from visually rich documents using visual span representations","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3137695810","doi":"https://doi.org/10.14778/3446095.3446104","mag":"3137695810"},"language":"en","primary_location":{"id":"doi:10.14778/3446095.3446104","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3446095.3446104","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","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/A5014228532","display_name":"Ritesh Sarkhel","orcid":"https://orcid.org/0000-0002-9116-1517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ritesh Sarkhel","raw_affiliation_strings":["The Ohio State Universtiy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State Universtiy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001906560","display_name":"Arnab Nandi","orcid":"https://orcid.org/0000-0002-4138-603X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnab Nandi","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5653,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.66471301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":"5","first_page":"822","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.993399977684021,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8589898347854614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.643510639667511},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5467246770858765},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.521430492401123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.508906364440918},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5021712779998779},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4978046417236328},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49060001969337463},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48999395966529846},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4859989583492279},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.435128778219223},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43389618396759033},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3446301817893982}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8589898347854614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.643510639667511},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5467246770858765},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.521430492401123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.508906364440918},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5021712779998779},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4978046417236328},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49060001969337463},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48999395966529846},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4859989583492279},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.435128778219223},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43389618396759033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3446301817893982},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3446095.3446104","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3446095.3446104","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W790941020","https://openalex.org/W1803802947","https://openalex.org/W1966382373","https://openalex.org/W2031489346","https://openalex.org/W2035015991","https://openalex.org/W2046797334","https://openalex.org/W2082163619","https://openalex.org/W2119162941","https://openalex.org/W2123442489","https://openalex.org/W2131801066","https://openalex.org/W2135479443","https://openalex.org/W2158051716","https://openalex.org/W2165698076","https://openalex.org/W2296232300","https://openalex.org/W2400661088","https://openalex.org/W2593390416","https://openalex.org/W2604259521","https://openalex.org/W2613881683","https://openalex.org/W2740924709","https://openalex.org/W2746326396","https://openalex.org/W2769041395","https://openalex.org/W2810187945","https://openalex.org/W2890139949","https://openalex.org/W2913389685","https://openalex.org/W2913699634","https://openalex.org/W2948784110","https://openalex.org/W2959716049","https://openalex.org/W2962772269","https://openalex.org/W2964308564","https://openalex.org/W2964346820","https://openalex.org/W3004330198","https://openalex.org/W3034864438","https://openalex.org/W4365799947"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W1511772879","https://openalex.org/W4379115841","https://openalex.org/W4200340037","https://openalex.org/W608917066","https://openalex.org/W4283652261","https://openalex.org/W585424826","https://openalex.org/W564602992"],"abstract_inverted_index":{"Along":[0],"with":[1,93],"textual":[2,67,119],"content,":[3],"visual":[4,28,56,65,91,110,128],"features":[5,122],"play":[6],"an":[7,141],"essential":[8],"role":[9],"in":[10,58,174],"the":[11,85,105,127],"semantics":[12],"of":[13,89,108,157],"visually":[14,43,50],"rich":[15,51],"documents.":[16,52],"Information":[17],"extraction":[18,159],"(IE)":[19],"tasks":[20],"perform":[21],"poorly":[22],"on":[23,147],"these":[24,27],"documents":[25],"if":[26],"cues":[29],"are":[30],"not":[31],"taken":[32],"into":[33,112,123],"account.":[34,124],"In":[35],"this":[36,136],"paper,":[37],"we":[38,78,97],"present":[39],"Artemis":[40,53,146],"-":[41],"a":[42,55,59,80,90,99,109,113,131,155],"aware,":[44],"machine-learning-based":[45],"IE":[46,70],"method":[47],"for":[48,69],"heterogeneous":[49,149],"represents":[54],"span":[57,92,111],"document":[60],"by":[61,116,134,140,169],"jointly":[62],"encoding":[63],"its":[64,118],"and":[66,120],"context":[68,87,107],"tasks.":[71,160],"Our":[72],"main":[73],"contribution":[74],"is":[75],"two-fold.":[76],"First,":[77],"develop":[79],"deep-learning":[81],"model":[82],"that":[83,103,163],"identifies":[84,126],"local":[86],"boundary":[88],"minimal":[94],"human-labeling.":[95],"Second,":[96],"describe":[98],"deep":[100],"neural":[101],"network":[102],"encodes":[104],"multimodal":[106],"fixed-length":[114],"vector":[115],"taking":[117],"layout-specific":[121],"It":[125],"span(s)":[129],"containing":[130],"named":[132],"entity":[133],"leveraging":[135],"learned":[137],"representation":[138],"followed":[139],"inference":[142],"task.":[143],"We":[144],"evaluate":[145],"four":[148],"datasets":[150],"from":[151],"different":[152],"domains":[153],"over":[154],"suite":[156],"information":[158],"Results":[161],"show":[162],"it":[164],"outperforms":[165],"state-of-the-art":[166],"text-based":[167],"methods":[168],"up":[170],"to":[171],"17":[172],"points":[173],"F1-score.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}