{"id":"https://openalex.org/W4396844015","doi":"https://doi.org/10.1145/3589335.3651946","title":"LLM Driven Web Profile Extraction for Identical Names","display_name":"LLM Driven Web Profile Extraction for Identical Names","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396844015","doi":"https://doi.org/10.1145/3589335.3651946"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651946","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651946","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097794995","display_name":"Prateek Sancheti","orcid":"https://orcid.org/0009-0004-8710-8328"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prateek Sancheti","raw_affiliation_strings":["Data Sciences and Analytics Center, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Data Sciences and Analytics Center, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088255710","display_name":"Kamalakar Karlapalem","orcid":"https://orcid.org/0000-0003-2528-7979"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kamalakar Karlapalem","raw_affiliation_strings":["Data Sciences and Analytics Center, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Data Sciences and Analytics Center, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090807575","display_name":"Kavita Vemuri","orcid":"https://orcid.org/0000-0003-4423-3896"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kavita Vemuri","raw_affiliation_strings":["Cognitive Science Lab, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Cognitive Science Lab, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5097794995"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.5149,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65268549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1616","last_page":"1625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9925000071525574,"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":0.715227484703064},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5655719637870789},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43055182695388794},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4122394323348999},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.12928125262260437},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08524203300476074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715227484703064},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5655719637870789},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43055182695388794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4122394323348999},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.12928125262260437},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08524203300476074}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589335.3651946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651946","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651946","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651946","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651946","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396844015.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1646278814","https://openalex.org/W2033073041","https://openalex.org/W2145093713","https://openalex.org/W2153911474","https://openalex.org/W2602953083","https://openalex.org/W2895715183","https://openalex.org/W2994093925","https://openalex.org/W3199958362","https://openalex.org/W4221104163","https://openalex.org/W4252110927","https://openalex.org/W4282010430","https://openalex.org/W4285236359"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0,23,41,169,186],"number":[1],"of":[2,16,39,44,50,64,119,174,188,196],"individuals":[3,66,139],"having":[4],"identical":[5,31,96],"names":[6,32],"on":[7,72,151],"the":[8,14,36,48,51,62,73,77,109,136,152,193],"internet":[9],"is":[10],"increasing.":[11],"Thus":[12],"making":[13],"task":[15],"searching":[17],"for":[18,206,227],"a":[19,55,80,85,156,199,208,228],"specific":[20,229],"individual":[21,38,46],"tedious.":[22],"user":[24],"must":[25],"vet":[26],"through":[27,99],"many":[28],"profiles":[29,63,91,125,132,149],"with":[30,126,217],"to":[33,35,93,135],"get":[34],"actual":[37],"interest.":[40],"online":[42],"presence":[43],"an":[45,100,203],"forms":[47],"profile":[49],"individual.":[52,230],"We":[53,83,142],"need":[54],"solution":[56,87,104,190],"that":[57,88,133,221],"helps":[58],"users":[59],"by":[60,67,145],"consolidating":[61,177],"such":[65,207],"retrieving":[68],"factual":[69],"information":[70,106,226],"available":[71],"web":[74,90,110],"and":[75,117,163,183],"providing":[76],"same":[78,137],"as":[79],"single":[81],"result.":[82],"present":[84],"novel":[86],"retrieves":[89],"belonging":[92],"those":[94],"bearing":[95],"Full":[97],"Names":[98],"end-to-end":[101],"pipeline.":[102],"Our":[103],"involves":[105],"retrieval":[107],"from":[108],"(extraction),":[111],"LLM-driven":[112],"Named":[113],"Entity":[114],"Extraction":[115],"(retrieval),":[116],"standardization":[118],"facts":[120,154],"using":[121,155],"Wikipedia,":[122],"which":[123],"returns":[124],"fourteen":[127],"multi-valued":[128],"attributes.":[129],"After":[130],"that,":[131],"correspond":[134],"real-world":[138],"are":[140],"determined.":[141],"accomplish":[143],"this":[144],"identifying":[146],"similarities":[147],"among":[148],"based":[150],"extracted":[153],"Prefix":[157],"Tree":[158],"inspired":[159],"data":[160],"structure":[161],"(validation)":[162],"utilizing":[164],"ChatGPT's":[165],"contextual":[166],"comprehension":[167],"(revalidation).":[168],"system":[170],"offers":[171],"varied":[172],"levels":[173],"strictness":[175],"while":[176],"these":[178],"profiles,":[179],"namely":[180],"strict,":[181],"relaxed,":[182],"loose":[184],"matching.":[185],"novelty":[187],"our":[189],"lies":[191],"in":[192],"innovative":[194],"use":[195],"GPT":[197],"--":[198],"highly":[200],"powerful":[201],"yet":[202],"unpredictable":[204],"tool,":[205],"nuanced":[209],"task.":[210],"A":[211],"study":[212],"involving":[213],"twenty":[214],"participants,":[215],"along":[216],"other":[218],"results,":[219],"found":[220],"one":[222],"could":[223],"effectively":[224],"retrieve":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}