{"id":"https://openalex.org/W4376166979","doi":"https://doi.org/10.1145/3539618.3591852","title":"Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection","display_name":"Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4376166979","doi":"https://doi.org/10.1145/3539618.3591852"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.05836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013651001","display_name":"Hsiu-Wei Yang","orcid":"https://orcid.org/0009-0005-5630-1077"},"institutions":[{"id":"https://openalex.org/I4210115483","display_name":"Thomson Reuters (Canada)","ror":"https://ror.org/01r4zz038","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210115483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hsiu-Wei Yang","raw_affiliation_strings":["Thomson Reuters Labs, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0005-5630-1077","affiliations":[{"raw_affiliation_string":"Thomson Reuters Labs, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210115483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101959107","display_name":"Abhinav Agrawal","orcid":"https://orcid.org/0009-0006-2742-4569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Agrawal","raw_affiliation_strings":["Thomson Reuters Labs, Bangalore, India"],"raw_orcid":"https://orcid.org/0009-0006-2742-4569","affiliations":[{"raw_affiliation_string":"Thomson Reuters Labs, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63071982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3349","last_page":"3353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.995199978351593,"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":0.834251344203949},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6321256160736084},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5881757736206055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5719085931777954},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5682780146598816},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4849384129047394},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4738084375858307},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46996375918388367},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43541476130485535},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.406019926071167},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33245009183883667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.326541930437088},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30535194277763367},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.10249024629592896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834251344203949},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6321256160736084},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5881757736206055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719085931777954},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5682780146598816},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4849384129047394},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4738084375858307},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46996375918388367},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43541476130485535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.406019926071167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33245009183883667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.326541930437088},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30535194277763367},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.10249024629592896},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3591852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.05836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05836","pdf_url":"https://arxiv.org/pdf/2305.05836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.05836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05836","pdf_url":"https://arxiv.org/pdf/2305.05836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376166979.pdf","grobid_xml":"https://content.openalex.org/works/W4376166979.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2037140704","https://openalex.org/W2098700435","https://openalex.org/W2133058591","https://openalex.org/W2163534337","https://openalex.org/W2606974598","https://openalex.org/W2777421064","https://openalex.org/W2886093254","https://openalex.org/W2964241181","https://openalex.org/W2986619406","https://openalex.org/W3000758063","https://openalex.org/W3003484198","https://openalex.org/W3003711898","https://openalex.org/W3106882134","https://openalex.org/W3113753692","https://openalex.org/W3120043490","https://openalex.org/W3137298232","https://openalex.org/W3152635971","https://openalex.org/W3176664887","https://openalex.org/W3202839357","https://openalex.org/W3214186955","https://openalex.org/W4206297296","https://openalex.org/W4210618466","https://openalex.org/W4214656930","https://openalex.org/W4287854446","https://openalex.org/W4290927927","https://openalex.org/W4304013646","https://openalex.org/W4385573834","https://openalex.org/W4385574165"],"related_works":["https://openalex.org/W2955175590","https://openalex.org/W2334378031","https://openalex.org/W2916255597","https://openalex.org/W3091569222","https://openalex.org/W4241018868","https://openalex.org/W2999302224","https://openalex.org/W1495833002","https://openalex.org/W3006227201","https://openalex.org/W2075635421","https://openalex.org/W2964631078"],"abstract_inverted_index":{"Accurate":[0],"Named":[1,26],"Entity":[2],"Recognition":[3],"(NER)":[4],"is":[5,75,104],"crucial":[6],"for":[7,45],"various":[8],"information":[9],"retrieval":[10],"tasks":[11],"in":[12,18,64,113],"industry.":[13],"However,":[14],"despite":[15],"significant":[16],"progress":[17],"traditional":[19],"NER":[20],"methods,":[21],"the":[22,56,69,76,90,98,107,115],"extraction":[23],"of":[24,58,71,109],"Complex":[25],"Entities":[27],"remains":[28],"a":[29,38],"relatively":[30],"unexplored":[31],"area.":[32],"In":[33],"this":[34,74],"paper,":[35],"we":[36],"propose":[37],"novel":[39],"system":[40],"that":[41,89],"combines":[42],"object":[43],"detection":[44],"Document":[46],"Layout":[47],"Analysis":[48],"(DLA)":[49],"with":[50],"weakly":[51],"supervised":[52,99],"learning":[53],"to":[54,68,79,83],"address":[55],"challenge":[57],"extracting":[59],"discontinuous":[60],"complex":[61],"named":[62],"entities":[63],"legal":[65],"documents.":[66],"Notably,":[67],"best":[70],"our":[72,110],"knowledge,":[73],"first":[77],"work":[78],"apply":[80],"weak":[81],"supervision":[82],"DLA.":[84],"Our":[85],"experimental":[86],"results":[87],"show":[88],"model":[91],"trained":[92],"solely":[93],"on":[94,117],"pseudo":[95],"labels":[96],"outperforms":[97],"baseline":[100],"when":[101],"gold-standard":[102],"data":[103],"limited,":[105],"highlighting":[106],"effectiveness":[108],"proposed":[111],"approach":[112],"reducing":[114],"dependency":[116],"annotated":[118],"data.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}