{"id":"https://openalex.org/W4387846497","doi":"https://doi.org/10.1145/3583780.3615207","title":"Learning Sparse Lexical Representations Over Specified Vocabularies for Retrieval","display_name":"Learning Sparse Lexical Representations Over Specified Vocabularies for Retrieval","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387846497","doi":"https://doi.org/10.1145/3583780.3615207"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615207","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615207","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615207","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081972748","display_name":"Jeffrey M. Dudek","orcid":"https://orcid.org/0000-0001-9980-0320"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey M. Dudek","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9980-0320","affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021205962","display_name":"Weize Kong","orcid":"https://orcid.org/0009-0004-2201-0127"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weize Kong","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0004-2201-0127","affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020073903","display_name":"Cheng Li","orcid":"https://orcid.org/0000-0003-0678-1357"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Li","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0678-1357","affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029748423","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0000-0002-1685-2895"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1685-2895","affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032248436","display_name":"Michael Bendersky","orcid":"https://orcid.org/0000-0002-2941-6240"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bendersky","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2941-6240","affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3865","last_page":"3869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9958000183105469,"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/interpretability","display_name":"Interpretability","score":0.8380590677261353},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8069814443588257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7829089164733887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.616773784160614},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5704381465911865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5136458277702332},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4386489987373352},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3708493411540985},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3304005265235901}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8380590677261353},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8069814443588257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829089164733887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616773784160614},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5704381465911865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5136458277702332},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4386489987373352},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3708493411540985},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3304005265235901},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615207","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615207","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3583780.3615207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615207","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615207","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387846497.pdf","grobid_xml":"https://content.openalex.org/works/W4387846497.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2897754576","https://openalex.org/W2964600737","https://openalex.org/W2980555592","https://openalex.org/W2996232440","https://openalex.org/W3021397474","https://openalex.org/W3133376386","https://openalex.org/W3154280800","https://openalex.org/W3154755316","https://openalex.org/W3172119680","https://openalex.org/W3188983256","https://openalex.org/W4284663260","https://openalex.org/W4308670109","https://openalex.org/W4384890771","https://openalex.org/W6629627396"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"A":[0],"recent":[1],"line":[2],"of":[3,18],"work":[4,23],"in":[5,35],"first-stage":[6],"Neural":[7],"Information":[8],"Retrieval":[9],"has":[10,27],"focused":[11],"on":[12,66],"learning":[13,61],"sparse":[14,63],"lexical":[15],"representations":[16],"instead":[17],"dense":[19],"embeddings.":[20],"One":[21],"such":[22],"is":[24],"SPLADE,":[25],"which":[26],"been":[28],"shown":[29],"to":[30,32,60],"lead":[31],"state-of-the-art":[33],"results":[34],"both":[36],"the":[37,67],"in-domain":[38],"and":[39,49],"zero-shot":[40],"settings,":[41],"can":[42],"leverage":[43],"inverted":[44],"indices":[45],"for":[46],"efficient":[47],"retrieval,":[48],"offers":[50],"enhanced":[51],"interpretability.":[52],"However,":[53],"existing":[54],"SPLADE":[55],"models":[56],"are":[57],"fundamentally":[58],"limited":[59],"a":[62],"representation":[64],"based":[65],"native":[68],"BERT":[69],"WordPiece":[70],"vocabulary.":[71]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}