{"id":"https://openalex.org/W4385572993","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.16","title":"Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching","display_name":"Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572993","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.16"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-industry.16","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-industry.16","pdf_url":"https://aclanthology.org/2022.emnlp-industry.16.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-industry.16.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090130877","display_name":"Justin Chiu","orcid":"https://orcid.org/0009-0000-9304-216X","observed_orcids":["https://orcid.org/0009-0000-9304-216X"]},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Justin Chiu","raw_affiliation_strings":["Rakuten Group Inc","Rakuten Institute of Technology","Rakuten Institute of Technology Rakuten Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Group Inc","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Institute of Technology","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Institute of Technology Rakuten Group Inc","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039159478","display_name":"Keiji Shinzato","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiji Shinzato","raw_affiliation_strings":["Rakuten Group Inc","Rakuten Institute of Technology","Rakuten Institute of Technology Rakuten Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rakuten Group Inc","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Institute of Technology","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Institute of Technology Rakuten Group Inc","institution_ids":["https://openalex.org/I1301041018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1301041018"],"apc_list":null,"apc_paid":null,"fwci":0.3507,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5647653,"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":"161","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7080000042915344,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7080000042915344,"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/T10028","display_name":"Topic Modeling","score":0.260699987411499,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.003100000089034438,"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/product-matching","display_name":"product matching","score":0.9850000143051147},{"id":"https://openalex.org/keywords/e-commerce","display_name":"e-commerce","score":0.7329999804496765},{"id":"https://openalex.org/keywords/training-data-annotation","display_name":"training data annotation","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8847938179969788},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8358138799667358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935478687286377},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6532556414604187},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5790889263153076},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5123571157455444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487325519323349},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4101133644580841},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37251725792884827},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36972057819366455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3659136891365051},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15803992748260498},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06933414936065674},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-industry.16","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-industry.16","pdf_url":"https://aclanthology.org/2022.emnlp-industry.16.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-industry.16","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.16","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-industry.16","pdf_url":"https://aclanthology.org/2022.emnlp-industry.16.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572993.pdf","grobid_xml":"https://content.openalex.org/works/W4385572993.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1969221592","https://openalex.org/W2167757616","https://openalex.org/W2593864460","https://openalex.org/W2807329228","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W3014705052","https://openalex.org/W3015883388","https://openalex.org/W3038572442","https://openalex.org/W3097013020","https://openalex.org/W3118668786","https://openalex.org/W3157758108","https://openalex.org/W3177415603","https://openalex.org/W4287645694","https://openalex.org/W6929257818"],"related_works":["https://openalex.org/W4389524353","https://openalex.org/W3179615045","https://openalex.org/W3080592272","https://openalex.org/W7214092697","https://openalex.org/W4286908394","https://openalex.org/W3116251907","https://openalex.org/W4398186370","https://openalex.org/W4392970221","https://openalex.org/W3093334098","https://openalex.org/W4378472638"],"abstract_inverted_index":{"Matching":[0],"a":[1,60,73,87,95,125],"seller":[2],"listed":[3],"item":[4],"to":[5,75,93],"an":[6,10,14],"appropriate":[7],"product":[8,121],"is":[9,150,161],"important":[11],"step":[12],"for":[13,35,63,83,147,158],"e-commerce":[15,127],"platform.With":[16],"the":[17,115,120,136],"recent":[18],"advancement":[19],"in":[20],"deep":[21],"learning,":[22],"there":[23],"are":[24,38,52,59],"different":[25],"encoder":[26],"based":[27,56],"approaches":[28,41,47,55],"being":[29],"proposed":[30],"as":[31],"solution.When":[32],"textual":[33],"data":[34,71,82,104,117,138,149,160],"two":[36],"products":[37],"available,":[39,151],"cross-encoder":[40,70,88,116,137],"encode":[42,48],"them":[43,49],"jointly":[44],"while":[45],"bi-encoder":[46,84],"separately.Since":[50],"cross-encoders":[51],"computationally":[53],"heavy,":[54],"on":[57,100,110,119],"bi-encoders":[58],"common":[61],"practice":[62],"this":[64,66],"challenge.In":[65],"paper,":[67],"we":[68],"propose":[69],"annotation;":[72],"technique":[74,90],"annotate":[76],"or":[77,105],"refine":[78],"human":[79],"annotated":[80,111],"training":[81,103,112,148,159],"models":[85],"using":[86,124],"model.This":[89],"enables":[91],"us":[92],"build":[94],"robust":[96],"model":[97,108],"without":[98],"annotation":[99,118,139,146,157],"newly":[101],"collected":[102],"further":[106],"improve":[107],"performance":[109],"data.We":[113],"evaluate":[114],"matching":[122],"task":[123],"real-world":[126],"dataset":[128],"containing":[129],"104":[130],"million":[131],"products.Experimental":[132],"results":[133],"show":[134],"that":[135],"improves":[140],"4%":[141],"absolute":[142,154],"accuracy":[143,155],"when":[144,156],"no":[145],"and":[152],"2%":[153],"available.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-08-05T00:00:00"}