{"id":"https://openalex.org/W4290944299","doi":"https://doi.org/10.1145/3534678.3539064","title":"Learning Supplementary NLP Features for CTR Prediction in Sponsored Search","display_name":"Learning Supplementary NLP Features for CTR Prediction in Sponsored Search","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290944299","doi":"https://doi.org/10.1145/3534678.3539064"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539064","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539064","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100391568","display_name":"Dong Wang","orcid":"https://orcid.org/0009-0008-7738-1688"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Microsoft Corporation, Beijing, China","Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026114186","display_name":"Shaoguang Yan","orcid":"https://orcid.org/0009-0009-1990-5743"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoguang Yan","raw_affiliation_strings":["Microsoft Corporation, Beijing, China","Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069555295","display_name":"Yunqing Xia","orcid":"https://orcid.org/0009-0005-8608-574X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqing Xia","raw_affiliation_strings":["Microsoft Corporation, Beijing, China","Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010294597","display_name":"Kav\u00e9 Salamatian","orcid":"https://orcid.org/0000-0001-5557-9134"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kav\u00e9 Salamatian","raw_affiliation_strings":["University of Savoie & Tallinn University of Technology, Annecy, France"],"affiliations":[{"raw_affiliation_string":"University of Savoie & Tallinn University of Technology, Annecy, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079468107","display_name":"Weiwei Deng","orcid":"https://orcid.org/0000-0002-5380-4219"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Deng","raw_affiliation_strings":["Microsoft Corporation, Beijing, China","Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100360194","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0001-5303-9804"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Microsoft Corporation, Beijing, China","Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia (5/F,Beijing Sigma Center No.49, Zhichun Road,Haidian District Beijing 100190, P.R.C. - China)","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100391568"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.3109,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83309165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4010","last_page":"4020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9983999729156494,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9983999729156494,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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/T10609","display_name":"Digital Marketing and Social Media","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.7586573362350464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7022449970245361},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.690713107585907},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6863572597503662},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5239741206169128},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.510966420173645},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.49750450253486633},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4766850471496582},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4531533718109131},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4512374699115753},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43779462575912476},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.42643263936042786},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4211300313472748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3407006561756134},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.28847241401672363},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07362204790115356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586573362350464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7022449970245361},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.690713107585907},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6863572597503662},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5239741206169128},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.510966420173645},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.49750450253486633},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4766850471496582},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4531533718109131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4512374699115753},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43779462575912476},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.42643263936042786},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4211300313472748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3407006561756134},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28847241401672363},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07362204790115356},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539064","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539064","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04219734v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04219734","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug 2022, Washington DC USA, United States. pp.4010-4020, ⟨10.1145/3534678.3539064⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3534678.3539064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539064","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539064","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4290944299.pdf","grobid_xml":"https://content.openalex.org/works/W4290944299.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1598508708","https://openalex.org/W2015772503","https://openalex.org/W2028706510","https://openalex.org/W2074694452","https://openalex.org/W2076618162","https://openalex.org/W2194775991","https://openalex.org/W2295739661","https://openalex.org/W2475334473","https://openalex.org/W2610314927","https://openalex.org/W2748787960","https://openalex.org/W2887783173","https://openalex.org/W2950445386","https://openalex.org/W2950960796","https://openalex.org/W2955624969","https://openalex.org/W2982157312","https://openalex.org/W2984020950","https://openalex.org/W3035582980","https://openalex.org/W3093681740","https://openalex.org/W3094444847","https://openalex.org/W3128746741","https://openalex.org/W3154079701","https://openalex.org/W4236965008","https://openalex.org/W4249138131","https://openalex.org/W6602670149"],"related_works":["https://openalex.org/W4398232961","https://openalex.org/W2494338568","https://openalex.org/W1495042958","https://openalex.org/W4294975608","https://openalex.org/W4396920741","https://openalex.org/W2923727989","https://openalex.org/W4247091536","https://openalex.org/W3081652108","https://openalex.org/W2976476443","https://openalex.org/W4387982773"],"abstract_inverted_index":{"In":[0,158],"sponsored":[1],"search":[2],"engines,":[3],"pre-trained":[4,22],"language":[5,23,32,68,108],"models":[6,24,33],"have":[7],"shown":[8],"promising":[9],"performance":[10,127],"improvements":[11],"on":[12,40,111],"Click-Through-Rate":[13],"(CTR)":[14],"prediction.":[15],"A":[16],"widely":[17],"used":[18,71],"approach":[19,86],"for":[20],"utilizing":[21],"in":[25,101,128,154],"CTR":[26,81,90,129,155,166],"prediction":[27,82,91,130,156,167],"consists":[28],"of":[29,43,55],"fine-tuning":[30],"the":[31,44,48,53,60,89,107,112,125,137,146,151,161],"with":[34],"click":[35],"labels":[36],"and":[37,96,143,150],"early":[38],"stopping":[39],"peak":[41,113],"value":[42],"obtained":[45],"Area":[46],"Under":[47],"ROC":[49],"Curve":[50],"(AUC).":[51],"Thereafter":[52],"output":[54],"these":[56],"fine-tuned":[57],"models,":[58],"i.e.,":[59],"final":[61],"score":[62],"or":[63],"intermediate":[64],"embedding":[65],"generated":[66],"by":[67],"model,":[69],"is":[70,139],"as":[72],"a":[73],"new":[74,147],"Natural":[75],"Language":[76],"Processing":[77],"(NLP)":[78],"feature":[79],"into":[80],"baseline.":[83,157],"This":[84],"cascade":[85],"avoids":[87],"complicating":[88],"baseline,":[92],"while":[93],"keeping":[94],"flexibility":[95],"agility.":[97],"However,":[98],"we":[99],"show":[100],"this":[102],"work":[103],"that":[104,123,136],"calibrating":[105],"separately":[106],"model":[109,115,131],"based":[110],"single":[114],"AUC":[116],"does":[117],"not":[118],"always":[119],"yield":[120],"NLP":[121,148,162],"features":[122,149,153,163],"give":[124],"best":[126],"ultimately.":[132],"Our":[133],"analysis":[134],"reveals":[135],"misalignment":[138],"due":[140],"to":[141],"overlap":[142,171],"redundancy":[144],"between":[145],"existing":[152],"other":[159],"words,":[160],"can":[164,172],"improve":[165],"better":[168],"if":[169],"such":[170],"be":[173],"reduced.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}