{"id":"https://openalex.org/W4385688528","doi":"https://doi.org/10.1145/3578337.3605126","title":"CSurF: Sparse Lexical Retrieval through Contextualized Surface Forms","display_name":"CSurF: Sparse Lexical Retrieval through Contextualized Surface Forms","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4385688528","doi":"https://doi.org/10.1145/3578337.3605126"},"language":"en","primary_location":{"id":"doi:10.1145/3578337.3605126","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578337.3605126","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578337.3605126","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 2023 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3578337.3605126","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101559598","display_name":"Zhen Fan","orcid":"https://orcid.org/0000-0001-6196-1057"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Fan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053131232","display_name":"Luyu Gao","orcid":"https://orcid.org/0000-0002-4239-383X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luyu Gao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101559598"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09021338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7723182439804077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6483293771743774},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.643793523311615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6347180008888245},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5608883500099182},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5457373261451721},{"id":"https://openalex.org/keywords/lexical-semantics","display_name":"Lexical semantics","score":0.5032972693443298},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4891839325428009},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4751862585544586},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4455733597278595},{"id":"https://openalex.org/keywords/lexical-item","display_name":"Lexical item","score":0.4301723837852478},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41593292355537415},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3630121946334839},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3629811406135559},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15232792496681213},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0886366069316864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723182439804077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6483293771743774},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.643793523311615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6347180008888245},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5608883500099182},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5457373261451721},{"id":"https://openalex.org/C98954769","wikidata":"https://www.wikidata.org/wiki/Q1759657","display_name":"Lexical semantics","level":3,"score":0.5032972693443298},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4891839325428009},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4751862585544586},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4455733597278595},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.4301723837852478},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41593292355537415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3630121946334839},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3629811406135559},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15232792496681213},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0886366069316864},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578337.3605126","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578337.3605126","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578337.3605126","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 2023 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3578337.3605126","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578337.3605126","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578337.3605126","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 2023 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385688528.pdf","grobid_xml":"https://content.openalex.org/works/W4385688528.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2070740689","https://openalex.org/W2104049510","https://openalex.org/W2117473841","https://openalex.org/W2534136119","https://openalex.org/W2648699835","https://openalex.org/W2783640434","https://openalex.org/W2963961878","https://openalex.org/W2979826702","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3023238803","https://openalex.org/W3154280800","https://openalex.org/W3155895380","https://openalex.org/W3184918446","https://openalex.org/W3205509771","https://openalex.org/W4205480697","https://openalex.org/W4231856373","https://openalex.org/W4236329806","https://openalex.org/W4252076394","https://openalex.org/W4255790188","https://openalex.org/W4284663260","https://openalex.org/W4306317212","https://openalex.org/W4327499170","https://openalex.org/W4327644077","https://openalex.org/W6601899773","https://openalex.org/W6636625392"],"related_works":["https://openalex.org/W1839466965","https://openalex.org/W4323076479","https://openalex.org/W4375869227","https://openalex.org/W84249500","https://openalex.org/W3186604040","https://openalex.org/W2186094699","https://openalex.org/W2386897213","https://openalex.org/W2758987059","https://openalex.org/W2491471938","https://openalex.org/W2171998564"],"abstract_inverted_index":{"Lexical":[0],"exact-match":[1,48,127,167,173],"systems":[2,183],"perform":[3,85],"text":[4],"retrieval":[5,13,49,88,120,168],"efficiently":[6,123],"with":[7,62],"sparse":[8,86,106],"matching":[9],"signals":[10],"and":[11,27,41,66,74,95,113,132,150,169],"fast":[12],"through":[14,126],"inverted":[15],"lists,":[16],"but":[17],"naturally":[18],"suffer":[19],"from":[20],"the":[21,37,42,161],"mismatch":[22,163],"between":[23],"lexical":[24,47,59,71,166,172,179],"surface":[25,38,52,60,111,130],"form":[26,39,61,72,112],"implicit":[28],"term":[29,43,117,148,151],"semantics.":[30],"This":[31,80],"paper":[32],"proposes":[33],"to":[34,84,91,143],"directly":[35],"bridge":[36],"space":[40,45],"semantics":[44],"in":[46,105,146,165],"via":[50,138],"contextualized":[51,76],"forms":[53],"(CSF).":[54],"Each":[55],"CSF":[56,136],"pairs":[57],"a":[58,63,70,75,98],"context":[64],"source,":[65],"is":[67,82],"represented":[68],"by":[69,89],"weight":[73],"semantic":[77,114,140],"vector":[78],"representation.":[79],"framework":[81],"able":[83],"lexicon-based":[87],"learning":[90],"represent":[92],"each":[93,135],"query":[94],"document":[96],"as":[97,178,184],"\"bag-of-CSFs\",":[99],"simultaneously":[100],"addressing":[101],"two":[102],"key":[103],"factors":[104],"retrieval:":[107],"vocabulary":[108],"expansion":[109],"of":[110,116,128],"representation":[115],"meaning.":[118],"At":[119],"time,":[121],"it":[122],"matches":[124],"CSFs":[125],"learned":[129],"forms,":[131],"effectively":[133],"scores":[134],"pair":[137],"contextual":[139],"representations,":[141],"leading":[142],"joint":[144],"improvement":[145],"both":[147],"match":[149,182],"scoring.":[152],"Multiple":[153],"experiments":[154],"show":[155],"that":[156],"this":[157],"approach":[158],"successfully":[159],"resolves":[160],"main":[162],"issues":[164],"outperforms":[170],"state-of-the-art":[171],"systems,":[174],"reaching":[175],"comparable":[176],"accuracy":[177],"all-to-all":[180],"soft":[181],"an":[185],"efficient":[186],"exact-match-based":[187],"system.":[188]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}