{"id":"https://openalex.org/W3134281122","doi":"https://doi.org/10.1145/3404835.3463093","title":"A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models","display_name":"A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3134281122","doi":"https://doi.org/10.1145/3404835.3463093","mag":"3134281122"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th 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/2103.03335","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Iurii Mokrii","orcid":null},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Iurii Mokrii","raw_affiliation_strings":["HSE University, Moscow, Russian Fed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HSE University, Moscow, Russian Fed","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leonid Boytsov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Boytsov","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pavel Braslavski","orcid":null},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I130823665","display_name":"Ural Federal University","ror":"https://ror.org/00hs7dr46","country_code":"RU","type":"education","lineage":["https://openalex.org/I130823665"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Braslavski","raw_affiliation_strings":["Ural Federal University & HSE University, Yekaterinburg, Russian Fed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ural Federal University & HSE University, Yekaterinburg, Russian Fed","institution_ids":["https://openalex.org/I130823665","https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.099,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8909651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2081","last_page":"2085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.7447999715805054},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7287999987602234},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.58160001039505},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5221999883651733},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5110999941825867},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.39320001006126404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775999903678894},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7447999715805054},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7287999987602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6183000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867000222206116},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.58160001039505},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5042999982833862},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3404835.3463093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.03335","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03335","pdf_url":"https://arxiv.org/pdf/2103.03335","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"},{"id":"pmh:oai:elar.urfu.ru:10995/111587","is_oa":true,"landing_page_url":"http://elar.urfu.ru/handle/10995/111587","pdf_url":null,"source":{"id":"https://openalex.org/S4306401522","display_name":"Electronic scientific archive of UrFU (Ural Federal University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130823665","host_organization_name":"Ural Federal University","host_organization_lineage":["https://openalex.org/I130823665"],"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":"SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"info:eu-repo/semantics/submittedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.03335","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.03335","pdf_url":"https://arxiv.org/pdf/2103.03335","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1989373893","https://openalex.org/W2024932032","https://openalex.org/W2102698119","https://openalex.org/W2135985057","https://openalex.org/W2610935556","https://openalex.org/W2910577570","https://openalex.org/W2912924812","https://openalex.org/W2922386288","https://openalex.org/W2963748441","https://openalex.org/W2964054038","https://openalex.org/W2971209824","https://openalex.org/W2998679789","https://openalex.org/W3100038904","https://openalex.org/W3104894527","https://openalex.org/W3144312515"],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,50,96,128,135],"high":[2],"annotation":[3],"costs":[4],"making":[5],"the":[6,137,142],"best":[7],"use":[8],"of":[9,26,28,57,62,69,80,118,141,150],"existing":[10],"human-created":[11],"training":[12,97,108],"data":[13],"is":[14,133],"an":[15],"important":[16],"research":[17],"direction.":[18],"We,":[19],"therefore,":[20],"carry":[21],"out":[22],"a":[23,47,51,54,66,73,102,115,122,151],"systematic":[24],"evaluation":[25,75],"transferability":[27],"BERT-based":[29],"neural":[30],"ranking":[31],"models":[32],"across":[33],"five":[34],"English":[35],"datasets.":[36],"Previous":[37],"studies":[38],"focused":[39],"primarily":[40],"on":[41,98,109],"zero-shot":[42],"and":[43,77],"few-shot":[44,143],"transfer":[45,94,129],"from":[46],"large":[48],"dataset":[49,52],"with":[53,111],"small":[55],"number":[56,68,117],"queries.":[58],"In":[59],"contrast,":[60],"each":[61],"our":[63,81],"collections":[64],"has":[65],"substantial":[67],"queries,":[70],"which":[71],"enables":[72],"full-shot":[74],"mode":[76],"improves":[78],"reliability":[79],"results.":[82],"Furthermore,":[83],"since":[84],"source":[85],"datasets":[86],"licences":[87],"often":[88],"prohibit":[89],"commercial":[90],"use,":[91],"we":[92],"compare":[93],"learning":[95],"pseudo-labels":[99],"generated":[100],"by":[101],"BM25":[103],"scorer.":[104],"We":[105],"find":[106],"that":[107],"pseudo-labels---possibly":[110],"subsequent":[112],"fine-tuning":[113],"using":[114],"modest":[116],"annotated":[119],"queries---can":[120],"produce":[121],"competitive":[123],"or":[124],"better":[125],"model":[126],"compared":[127],"learning.":[130],"Yet,":[131],"it":[132],"necessary":[134],"improve":[136],"stability":[138],"and/or":[139],"effectiveness":[140],"training,":[144],"which,":[145],"sometimes,":[146],"can":[147],"degrade":[148],"performance":[149],"pretrained":[152],"model.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-03-15T00:00:00"}