{"id":"https://openalex.org/W4409158310","doi":"https://doi.org/10.1145/3690624.3709427","title":"A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification","display_name":"A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409158310","doi":"https://doi.org/10.1145/3690624.3709427"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","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/A5017480421","display_name":"D. Subhalingam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Subhalingam","raw_affiliation_strings":["KnowDis AI, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0004-7497-9722","affiliations":[{"raw_affiliation_string":"KnowDis AI, Delhi, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027939157","display_name":"Keshav Kolluru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keshav Kolluru","raw_affiliation_strings":["KnowDis AI, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0003-9963-9401","affiliations":[{"raw_affiliation_string":"KnowDis AI, Delhi, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042262991","display_name":"Mausam Mausam","orcid":"https://orcid.org/0000-0003-4088-4296"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mausam","raw_affiliation_strings":["Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-4088-4296","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5098724362","display_name":"Saurabh Singal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Singal","raw_affiliation_strings":["KnowDis AI, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0004-2556-6905","affiliations":[{"raw_affiliation_string":"KnowDis AI, Delhi, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5206,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81931199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2560","last_page":"2571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9779999852180481,"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/T11719","display_name":"Data Quality and Management","score":0.9771000146865845,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6697344779968262},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6518937349319458},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5296131372451782},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.52643883228302},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3536838889122009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15670034289360046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11492791771888733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6697344779968262},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6518937349319458},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5296131372451782},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.52643883228302},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3536838889122009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15670034289360046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11492791771888733},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1969221592","https://openalex.org/W1975879668","https://openalex.org/W2020278455","https://openalex.org/W2024105308","https://openalex.org/W2132667892","https://openalex.org/W2164777277","https://openalex.org/W2805173585","https://openalex.org/W2951865668","https://openalex.org/W3034300118","https://openalex.org/W3034999214","https://openalex.org/W3185054725","https://openalex.org/W3196049532","https://openalex.org/W4212764525","https://openalex.org/W4234859835","https://openalex.org/W4236575201","https://openalex.org/W4283750777","https://openalex.org/W4285306484","https://openalex.org/W4287854712","https://openalex.org/W4302568324","https://openalex.org/W4385570423","https://openalex.org/W4385570676","https://openalex.org/W4385571705","https://openalex.org/W4389393499","https://openalex.org/W4400529373","https://openalex.org/W4400530533"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"the":[1,4,41,48,54,80,109,129,144,155,208,215,242,250,264],"e-commerce":[2,233],"domain,":[3],"accurate":[5,132],"extraction":[6,217],"of":[7,43,131,203,210,218,239,244,259],"attribute-value":[8,51,149,219,247],"pairs":[9,52,248],"(e.g.,":[10],"B":[11],"rand":[12],":":[13],"Apple":[14],")":[15],"from":[16,199],"product":[17],"titles":[18],"and":[19,28,206],"user":[20],"search":[21,27],"queries":[22],"is":[23,40],"crucial":[24],"for":[25,37,50,73,82,112,158,266],"enhancing":[26],"recommendation":[29],"systems.":[30],"A":[31],"major":[32],"challenge":[33],"with":[34,76],"neural":[35],"models":[36],"this":[38],"task":[39],"lack":[42],"high-quality":[44],"training":[45,74,145,159,209],"data,":[46,78,174],"as":[47],"annotations":[49],"in":[53,128,171,241],"available":[55],"datasets":[56],"are":[57,165],"often":[58],"incomplete.":[59],"To":[60],"address":[61],"this,":[62],"we":[63,135],"introduce":[64],"G":[65,87,115,137,182,190,267],"en":[66,88,116,138,183,191,268],"T":[67,89,117,139,184,192,269],"o":[68,90,118,140,185,193,270],"C,":[69],"a":[70,83,93,103,200,236,256],"model":[71,96,106,223,272],"designed":[72],"directly":[75],"partially-labeled":[77,173,204],"eliminating":[79],"necessity":[81],"fully":[84],"annotated":[85],"dataset.":[86],"C":[91,119,141,271],"employs":[92],"marker-augmented":[94],"generative":[95],"to":[97,142,147,177,181,197],"identify":[98],"potential":[99],"attributes,":[100],"followed":[101],"by":[102],"token":[104],"classification":[105],"that":[107],"determines":[108],"associated":[110],"values":[111],"each":[113],"attribute.":[114],"outperforms":[120],"existing":[121,251],"state-of-the-art":[122],"models,":[123,163,213],"exhibiting":[124],"upto":[125],"56.3%":[126],"increase":[127,238],"number":[130,243],"extractions.":[133],"Furthermore,":[134],"utilize":[136],"regenerate":[143],"dataset":[146],"expand":[148],"annotations.":[150],"This":[151],"bootstrapping":[152],"substantially":[153],"improves":[154],"data":[156,205],"quality":[157],"other":[160],"standard":[161],"NER":[162],"which":[164],"typically":[166],"faster":[167],"but":[168],"less":[169],"capable":[170],"handling":[172],"enabling":[175],"them":[176],"achieve":[178],"comparable":[179],"performance":[180],"C.":[186],"Our":[187],"results":[188],"demonstrate":[189],"C's":[194],"unique":[195],"ability":[196],"learn":[198],"limited":[201],"set":[202],"improve":[207],"more":[211],"efficient":[212],"advancing":[214],"automated":[216],"pairs.":[220],"Finally,":[221],"our":[222],"has":[224],"been":[225],"successfully":[226],"integrated":[227],"into":[228],"IndiaMART,":[229],"India's":[230],"largest":[231],"B2B":[232],"platform,":[234],"achieving":[235,255],"significant":[237],"20.2%":[240],"correctly":[245],"identified":[246],"over":[249],"deployed":[252],"system":[253],"while":[254],"high":[257],"precision":[258],"89.5%.":[260],"We":[261],"have":[262],"released":[263],"code":[265],"at":[273],"https://github.com/KnowDisAI/GenToC.":[274]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}