{"id":"https://openalex.org/W4385572934","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.32","title":"Unsupervised Dense Retrieval for Scientific Articles","display_name":"Unsupervised Dense Retrieval for Scientific Articles","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572934","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.32"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-industry.32","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.32","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-industry.32","pdf_url":"https://aclanthology.org/2022.emnlp-industry.32.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.32.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100380761","display_name":"Dan Li","orcid":"https://orcid.org/0000-0001-6381-1087","observed_orcids":["https://orcid.org/0000-0001-6381-1087","https://orcid.org/0000-0002-7581-8865"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vikrant Yadav","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikrant Yadav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048053757","display_name":"Zubair Afzal","orcid":"https://orcid.org/0000-0001-7812-2399","observed_orcids":["https://orcid.org/0000-0001-7812-2399"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zubair Afzal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080654893","display_name":"George Tsatsaronis","orcid":"https://orcid.org/0000-0003-2116-2933","observed_orcids":["https://orcid.org/0000-0003-2116-2933"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Tsatsaronis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3452,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.45938006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8080999851226807,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8080999851226807,"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":0.1704999953508377,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dense-retrieval","display_name":"dense retrieval","score":0.8659999966621399},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.8569999933242798},{"id":"https://openalex.org/keywords/scientific-articles","display_name":"scientific articles","score":0.7129999995231628},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.847000002861023},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.8090000152587891},{"id":"https://openalex.org/keywords/passage-selection","display_name":"passage selection","score":0.6100000143051147},{"id":"https://openalex.org/keywords/elsevier","display_name":"Elsevier","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352322578430176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.721063494682312},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.709265410900116},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4903118908405304},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47510966658592224},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.4708523154258728},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.44172191619873047},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4262964129447937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3988780975341797},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-industry.32","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.32","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-industry.32","pdf_url":"https://aclanthology.org/2022.emnlp-industry.32.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.32","doi":"https://doi.org/10.18653/v1/2022.emnlp-industry.32","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.emnlp-industry.32","pdf_url":"https://aclanthology.org/2022.emnlp-industry.32.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":[{"id":"https://openalex.org/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572934.pdf","grobid_xml":"https://content.openalex.org/works/W4385572934.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1661745278","https://openalex.org/W2115584760","https://openalex.org/W2525778437","https://openalex.org/W2798991696","https://openalex.org/W2951534261","https://openalex.org/W2970641574","https://openalex.org/W3015883388","https://openalex.org/W3038572442","https://openalex.org/W3118668786","https://openalex.org/W3135367836","https://openalex.org/W3153015371","https://openalex.org/W3153624757","https://openalex.org/W3153833878","https://openalex.org/W3154280800","https://openalex.org/W3155895380","https://openalex.org/W3180663620","https://openalex.org/W3184918446","https://openalex.org/W3205509771","https://openalex.org/W3210968241","https://openalex.org/W3211633257","https://openalex.org/W4225104598","https://openalex.org/W4225644300","https://openalex.org/W4281493120","https://openalex.org/W4283710285","https://openalex.org/W4284669182","https://openalex.org/W4287207977","https://openalex.org/W4287645694","https://openalex.org/W4303684020","https://openalex.org/W4320813768","https://openalex.org/W6950037442"],"related_works":["https://openalex.org/W4311556096","https://openalex.org/W7077869830","https://openalex.org/W4380559094","https://openalex.org/W3187693843","https://openalex.org/W7005946396","https://openalex.org/W4391673302","https://openalex.org/W4389520221","https://openalex.org/W4385569963","https://openalex.org/W4312046631","https://openalex.org/W4417098468"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,55,68],"build":[4],"a":[5,31],"dense":[6,34],"retrieval":[7,35],"based":[8],"semantic":[9,88,110],"search":[10,89,96,111,121],"engine":[11,90,97,112],"on":[12,98],"scientific":[13],"articles":[14,49],"from":[15,58,80],"Elsevier.The":[16],"major":[17],"challenge":[18],"is":[19,22],"that":[20,41,108],"there":[21],"no":[23],"labeled":[24],"data":[25],"for":[26],"training":[27,45,64,116],"and":[28,76],"testing.We":[29],"apply":[30],"state-of-the-art":[32],"unsupervised":[33],"model":[36],"called":[37],"Generative":[38],"Pseudo":[39],"Labeling":[40],"generates":[42],"high-quality":[43],"pseudo":[44,115],"labels.Furthermore,":[46],"since":[47],"the":[48,66,81,87,92,99,105,109],"are":[50],"unbalanced":[51],"across":[52],"different":[53],"domains,":[54],"select":[56],"passages":[57],"multiple":[59],"domains":[60],"to":[61],"form":[62],"balanced":[63],"data.For":[65],"evaluation,":[67],"create":[69],"two":[70,100],"test":[71,101],"sets:":[72],"one":[73,77],"manually":[74],"annotated":[75],"automatically":[78],"created":[79],"meta-information":[82],"of":[83,104],"our":[84],"data.We":[85],"compare":[86],"with":[91,114],"currently":[93],"deployed":[94],"lexical":[95],"sets.The":[102],"results":[103],"experiment":[106],"show":[107],"trained":[113],"labels":[117],"can":[118],"significantly":[119],"improve":[120],"performance.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-08-05T00:00:00"}