{"id":"https://openalex.org/W4412888661","doi":"https://doi.org/10.18653/v1/2025.findings-acl.357","title":"Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval","display_name":"Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888661","doi":"https://doi.org/10.18653/v1/2025.findings-acl.357"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.357","pdf_url":"https://aclanthology.org/2025.findings-acl.357.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.357.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yubai Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Yubai Wei","raw_affiliation_strings":["University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology","institution_ids":["https://openalex.org/I118692353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011412438","display_name":"Jiale Han","orcid":"https://orcid.org/0000-0001-6477-0424"},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Jiale Han","raw_affiliation_strings":["University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology","institution_ids":["https://openalex.org/I118692353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052533101","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-3233-0907"},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology","institution_ids":["https://openalex.org/I118692353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118692353"],"apc_list":null,"apc_paid":null,"fwci":1.3614,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83218739,"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":"6856","last_page":"6870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9785000085830688,"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":0.9785000085830688,"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":0.8243644833564758},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7124463319778442},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.626727819442749},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3543224632740021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34996241331100464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243644833564758},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7124463319778442},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.626727819442749},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3543224632740021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34996241331100464}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.357","pdf_url":"https://aclanthology.org/2025.findings-acl.357.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.00363","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00363","pdf_url":"https://arxiv.org/pdf/2506.00363","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:repository.hkust.edu.hk:1783.1-168690","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168690","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.357","pdf_url":"https://aclanthology.org/2025.findings-acl.357.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307117","display_name":"HSBC Bank USA","ror":"https://ror.org/00t2kp174"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888661.pdf","grobid_xml":"https://content.openalex.org/works/W4412888661.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Text":[0],"embedding":[1,17,57],"models":[2,18,58,125],"play":[3],"a":[4,50,87],"cornerstone":[5],"role":[6],"in":[7,97,123],"AI":[8],"applications,":[9],"such":[10],"as":[11],"retrieval-augmented":[12],"generation":[13],"(RAG).While":[14],"general-purpose":[15,55],"text":[16,56],"demonstrate":[19],"strong":[20],"performance":[21],"on":[22],"generic":[23],"retrieval":[24,66,78,98],"benchmarks,":[25],"their":[26],"effectiveness":[27],"diminishes":[28],"when":[29],"applied":[30],"to":[31,59,80,109,126],"private":[32,60],"datasets":[33],"(e.g.,":[34],"company-specific":[35],"proprietary":[36],"data),":[37],"which":[38],"often":[39],"contain":[40],"specialized":[41],"terminology":[42],"and":[43,92,115],"lingo.In":[44],"this":[45,121],"work,":[46],"we":[47,69,100],"introduce":[48],"BMEmbed,":[49],"novel":[51],"method":[52],"for":[53,134],"adapting":[54,124],"datasets.By":[61],"leveraging":[62],"the":[63,74,118,130,135],"wellestablished":[64],"keyword-based":[65,77],"technique":[67],"(BM25),":[68],"construct":[70],"supervisory":[71],"signals":[72,107],"from":[73],"ranking":[75],"of":[76,89,120],"results":[79],"facilitate":[81],"model":[82],"adaptation.We":[83],"evaluate":[84],"BMEmbed":[85],"across":[86],"range":[88],"domains,":[90],"datasets,":[91],"models,":[93],"showing":[94],"consistent":[95],"improvements":[96],"performance.Moreover,":[99],"provide":[101],"empirical":[102],"insights":[103],"into":[104],"how":[105],"BM25-based":[106],"contribute":[108],"improving":[110],"embeddings":[111],"by":[112],"fostering":[113],"alignment":[114],"uniformity,":[116],"highlighting":[117],"value":[119],"approach":[122],"domain-specific":[127],"data.We":[128],"release":[129],"source":[131],"code":[132],"1":[133],"research":[136],"community.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}