{"id":"https://openalex.org/W4390723217","doi":"https://doi.org/10.48550/arxiv.2401.04055","title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval","display_name":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4390723217","doi":"https://doi.org/10.48550/arxiv.2401.04055"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.04055","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.04055","pdf_url":"https://arxiv.org/pdf/2401.04055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.04055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090437590","display_name":"Priyanka Mandikal","orcid":"https://orcid.org/0000-0002-6257-7417","observed_orcids":["https://orcid.org/0000-0002-6257-7417"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mandikal, Priyanka","raw_affiliation_strings":["The University of Texas at Austin , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin , USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490","observed_orcids":["https://orcid.org/0000-0002-4504-0490"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mooney, Raymond","raw_affiliation_strings":["The University of Texas at Austin , USA","Vancouver , BC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin , USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Vancouver , BC , Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9750999808311462,"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":0.9750999808311462,"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":0.02019999921321869,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/scientific-document-retrieval","display_name":"scientific document retrieval","score":0.968999981880188},{"id":"https://openalex.org/keywords/hybrid-retrieval-model","display_name":"hybrid retrieval model","score":0.7910000085830688},{"id":"https://openalex.org/keywords/dense-embeddings","display_name":"dense embeddings","score":0.8610000014305115},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7680000066757202},{"id":"https://openalex.org/keywords/health-information-retrieval","display_name":"medical information retrieval","score":0.6470000147819519},{"id":"https://openalex.org/keywords/cystic-fibrosis","display_name":"cystic fibrosis","score":0.9089999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494328022003174},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6886125802993774},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5445490479469299},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5148417353630066},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5122799277305603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5111988186836243},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5095298886299133},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49330511689186096},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41394466161727905},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.04055","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.04055","pdf_url":"https://arxiv.org/pdf/2401.04055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.04055","doi":"https://doi.org/10.48550/arxiv.2401.04055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.04055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.04055","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.04055","pdf_url":"https://arxiv.org/pdf/2401.04055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390723217.pdf","grobid_xml":"https://content.openalex.org/works/W4390723217.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3015883388","https://openalex.org/W3016913119","https://openalex.org/W4389524502"],"related_works":["https://openalex.org/W4200630182","https://openalex.org/W7134167849","https://openalex.org/W4400716800","https://openalex.org/W3200660033","https://openalex.org/W7161152276","https://openalex.org/W4387960904","https://openalex.org/W4383265562","https://openalex.org/W4411061114","https://openalex.org/W4385571931","https://openalex.org/W4381573351"],"abstract_inverted_index":{"Traditional":[0],"information":[1,94],"retrieval":[2,39,95],"is":[3],"based":[4],"on":[5,32,36],"sparse":[6],"bag-of-words":[7],"vector":[8],"representations":[9],"of":[10,44,49,85,99],"documents":[11],"and":[12,88],"queries.":[13],"More":[14],"recent":[15],"deep-learning":[16],"approaches":[17],"have":[18],"used":[19],"dense":[20,56],"embeddings":[21],"learned":[22],"using":[23],"a":[24,33,69],"transformer-based":[25],"large":[26],"language":[27],"model.":[28],"We":[29],"show":[30],"that":[31,47,72],"classic":[34],"benchmark":[35],"scientific":[37,101],"document":[38],"in":[40,93,96],"the":[41,59,83,97],"medical":[42],"domain":[43,98],"cystic":[45],"fibrosis,":[46],"both":[48],"these":[50,76],"models":[51],"perform":[52],"roughly":[53],"equivalently.":[54],"Notably,":[55],"vectors":[57],"from":[58],"state-of-the-art":[60],"SPECTER2":[61],"model":[62,71],"do":[63],"not":[64],"significantly":[65,79],"enhance":[66],"performance.":[67],"However,":[68],"hybrid":[70],"we":[73],"propose":[74],"combining":[75],"methods":[77],"yields":[78],"better":[80],"results,":[81],"underscoring":[82],"merits":[84],"integrating":[86],"classical":[87],"contemporary":[89],"deep":[90],"learning":[91],"techniques":[92],"specialized":[100],"documents.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-01-13T00:00:00"}