{"id":"https://openalex.org/W4384890771","doi":"https://doi.org/10.1145/3539618.3592065","title":"SparseEmbed: Learning Sparse Lexical Representations with Contextual Embeddings for Retrieval","display_name":"SparseEmbed: Learning Sparse Lexical Representations with Contextual Embeddings for Retrieval","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384890771","doi":"https://doi.org/10.1145/3539618.3592065"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3592065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592065","pdf_url":null,"source":null,"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 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3539618.3592065","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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/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/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":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2399","last_page":"2403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8522590398788452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926459908485413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426604986190796},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4532148241996765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44798898696899414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37819039821624756}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8522590398788452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926459908485413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426604986190796},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4532148241996765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44798898696899414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37819039821624756}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3592065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592065","pdf_url":null,"source":null,"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 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3539618.3592065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592065","pdf_url":null,"source":null,"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 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2117130368","https://openalex.org/W2811318564","https://openalex.org/W2897754576","https://openalex.org/W2996232440","https://openalex.org/W3021397474","https://openalex.org/W3034912391","https://openalex.org/W3134665270","https://openalex.org/W3154280800","https://openalex.org/W3154670582","https://openalex.org/W3154755316","https://openalex.org/W3172119680","https://openalex.org/W3184918446","https://openalex.org/W3188983256","https://openalex.org/W3194741792","https://openalex.org/W4284664419","https://openalex.org/W4290943593","https://openalex.org/W4306317003","https://openalex.org/W7054915730"],"related_works":["https://openalex.org/W1986582023","https://openalex.org/W2883749686","https://openalex.org/W2961085424","https://openalex.org/W2966829450","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044"],"abstract_inverted_index":{"In":[0,17,43],"dense":[1,12,55],"retrieval,":[2,19],"prior":[3],"work":[4],"has":[5],"largely":[6],"improved":[7],"retrieval":[8,67],"effectiveness":[9,38],"using":[10],"multi-vector":[11],"representations,":[13],"exemplified":[14],"by":[15],"ColBERT.":[16],"sparse":[18,32,53,71,94],"more":[20],"recent":[21],"work,":[22,45],"such":[23],"as":[24],"SPLADE,":[25,79],"demonstrated":[26],"that":[27,69],"one":[28],"can":[29],"also":[30],"learn":[31],"lexical":[33,72],"representations":[34,56,73,95],"to":[35,86,99],"achieve":[36],"comparable":[37],"while":[39],"enjoying":[40],"better":[41],"interpretability.":[42],"this":[44],"we":[46,61],"combine":[47],"the":[48,52,83],"strengths":[49],"of":[50],"both":[51,101],"and":[54,103],"for":[57],"first-stage":[58],"retrieval.":[59],"Specifically,":[60],"propose":[62],"SparseEmbed":[63],"-":[64],"a":[65],"novel":[66],"model":[68,81,88],"learns":[70],"with":[74,78,91],"contextual":[75,84],"embeddings.":[76],"Compared":[77,90],"our":[80,93],"leverages":[82],"embeddings":[85],"improve":[87],"expressiveness.":[89],"ColBERT,":[92],"are":[96],"trained":[97],"end-to-end":[98],"optimize":[100],"efficiency":[102],"effectiveness.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}