{"id":"https://openalex.org/W4384705126","doi":"https://doi.org/10.1145/3539618.3591644","title":"BLADE: Combining Vocabulary Pruning and Intermediate Pretraining for Scaleable Neural CLIR","display_name":"BLADE: Combining Vocabulary Pruning and Intermediate Pretraining for Scaleable Neural CLIR","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384705126","doi":"https://doi.org/10.1145/3539618.3591644"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591644","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591644","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/10.1145/3539618.3591644","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103112625","display_name":"Suraj Nair","orcid":"https://orcid.org/0000-0003-2283-7672"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suraj Nair","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-2283-7672","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062016266","display_name":"Eugene Yang","orcid":"https://orcid.org/0000-0002-0051-1535"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-0051-1535","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037074105","display_name":"Dawn Lawrie","orcid":"https://orcid.org/0000-0001-7347-7086"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-7347-7086","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036270568","display_name":"James Mayfield","orcid":"https://orcid.org/0000-0003-3866-3013"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Mayfield","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-3866-3013","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074322406","display_name":"Douglas W. Oard","orcid":"https://orcid.org/0000-0002-1696-0407"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas W. Oard","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-1696-0407","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73971482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1219","last_page":"1229"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8397449851036072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7220032215118408},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7203490734100342},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6551421284675598},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6459227204322815},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6368303298950195},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5966172218322754},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5577918887138367},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5452937483787537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10114258527755737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8397449851036072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7220032215118408},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7203490734100342},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6551421284675598},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6459227204322815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6368303298950195},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5966172218322754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5577918887138367},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5452937483787537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10114258527755737},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591644","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591644","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:10.1145/3539618.3591644","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591644","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1593271688","https://openalex.org/W2006832571","https://openalex.org/W2046456023","https://openalex.org/W2065472179","https://openalex.org/W2089379373","https://openalex.org/W2148972377","https://openalex.org/W2169724380","https://openalex.org/W2531638282","https://openalex.org/W2559992436","https://openalex.org/W2739738036","https://openalex.org/W2740321901","https://openalex.org/W2771976988","https://openalex.org/W2897754576","https://openalex.org/W2928384811","https://openalex.org/W2945127593","https://openalex.org/W2951534261","https://openalex.org/W3021397474","https://openalex.org/W3034746011","https://openalex.org/W3099446234","https://openalex.org/W3099744315","https://openalex.org/W3100806282","https://openalex.org/W3101279614","https://openalex.org/W3105234097","https://openalex.org/W3154280800","https://openalex.org/W3154755316","https://openalex.org/W3155114168","https://openalex.org/W3206127589","https://openalex.org/W4224983763","https://openalex.org/W4225727172","https://openalex.org/W4226112939","https://openalex.org/W4254478394","https://openalex.org/W4284663260","https://openalex.org/W4284664419","https://openalex.org/W4284880643","https://openalex.org/W4295885374","https://openalex.org/W4306317212","https://openalex.org/W4318718892","https://openalex.org/W6601026431","https://openalex.org/W6605614091","https://openalex.org/W6880033799"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W1976265003","https://openalex.org/W2054476758","https://openalex.org/W2370378377","https://openalex.org/W2048865712","https://openalex.org/W4210535024","https://openalex.org/W4237510188","https://openalex.org/W2130160813","https://openalex.org/W2350613701"],"abstract_inverted_index":{"Learning":[0],"sparse":[1,15,81],"representations":[2,13,59],"using":[3,36],"pretrained":[4,38],"language":[5,22,39],"models":[6,40,50],"enhances":[7],"the":[8,18,45,58],"monolingual":[9,106],"ranking":[10],"effectiveness.":[11],"Such":[12],"are":[14],"vectors":[16],"in":[17],"vocabulary":[19,86],"of":[20,48,60,121],"a":[21,79],"model":[23],"projected":[24],"from":[25,62],"document":[26],"terms.":[27],"Extending":[28],"such":[29],"approaches":[30],"to":[31,104,119],"Cross-Language":[32],"Information":[33],"Retrieval":[34],"(CLIR)":[35],"multilingual":[37,49],"poses":[41],"two":[42],"challenges.":[43],"First,":[44],"larger":[46],"vocabularies":[47],"affect":[51],"both":[52],"training":[53],"and":[54,112],"inference":[55],"efficiency.":[56],"Second,":[57],"terms":[61],"different":[63],"languages":[64],"with":[65,88,116],"similar":[66],"meanings":[67],"might":[68],"not":[69],"be":[70],"sufficiently":[71],"similar.":[72],"To":[73],"address":[74],"these":[75],"issues,":[76],"we":[77],"propose":[78],"learned":[80],"representation":[82],"model,":[83],"BLADE,":[84],"combining":[85],"pruning":[87],"intermediate":[89],"pre-training":[90],"based":[91],"on":[92,109],"cross-language":[93],"supervision.":[94],"Our":[95],"experiments":[96],"reveal":[97],"BLADE":[98],"significantly":[99],"reduces":[100],"indexing":[101],"time":[102],"compared":[103],"its":[105],"counterpart,":[107],"SPLADE,":[108],"machine-translated":[110],"documents,":[111],"it":[113],"generates":[114],"rankings":[115],"strengths":[117],"complementary":[118],"those":[120],"other":[122],"efficient":[123],"CLIR":[124],"methods.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}