{"id":"https://openalex.org/W4400525612","doi":"https://doi.org/10.1145/3626772.3657792","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval.","display_name":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval.","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400525612","doi":"https://doi.org/10.1145/3626772.3657792"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657792?download=true","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 47th International ACM SIGIR Conference on Research and Development in 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/10.1145/3626772.3657792?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086478796","display_name":"Guangyuan Ma","orcid":"https://orcid.org/0000-0001-6916-9611"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyuan Ma","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6916-9611","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325851","display_name":"Xing Wu","orcid":"https://orcid.org/0009-0004-3796-3705"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Wu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3796-3705","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077882811","display_name":"Zijia Lin","orcid":"https://orcid.org/0000-0002-1390-7424"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijia Lin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1390-7424","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018288181","display_name":"Songlin Hu","orcid":"https://orcid.org/0000-0002-7170-3809"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlin Hu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7170-3809","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72657315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1818","last_page":"1827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7757879495620728},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6213811635971069},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5727059841156006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149582028388977},{"id":"https://openalex.org/keywords/drop","display_name":"Drop (telecommunication)","score":0.5148862600326538},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48224955797195435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47627371549606323},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06591463088989258},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05972963571548462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757879495620728},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6213811635971069},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5727059841156006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149582028388977},{"id":"https://openalex.org/C2781345722","wikidata":"https://www.wikidata.org/wiki/Q5308388","display_name":"Drop (telecommunication)","level":2,"score":0.5148862600326538},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48224955797195435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47627371549606323},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06591463088989258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05972963571548462},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657792?download=true","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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657792?download=true","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 47th 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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400525612.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2130725040","https://openalex.org/W2912924812","https://openalex.org/W2963469388","https://openalex.org/W3099700870","https://openalex.org/W3154280800","https://openalex.org/W3155114168","https://openalex.org/W3188983256","https://openalex.org/W3206455169","https://openalex.org/W3212725701","https://openalex.org/W4206121183","https://openalex.org/W4246649926","https://openalex.org/W4252076394","https://openalex.org/W4284664419","https://openalex.org/W4375870261","https://openalex.org/W4377865280","https://openalex.org/W4384656691","https://openalex.org/W4385570296","https://openalex.org/W4385572504","https://openalex.org/W4385572770","https://openalex.org/W6600118084"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Masked":[0],"auto-encoder":[1,75,116,167],"pre-training":[2,45,77,168],"has":[3],"emerged":[4],"as":[5],"a":[6,44,103,114,118,159],"prevalent":[7],"technique":[8,46],"for":[9,39],"initializing":[10],"and":[11,28],"enhancing":[12],"dense":[13,33,90,134],"retrieval":[14,145,150],"systems.":[15],"It":[16],"generally":[17],"utilizes":[18],"additional":[19,52,155],"Transformer":[20],"decoder":[21,112],"blocks":[22],"to":[23,65,93,105,164],"provide":[24],"sustainable":[25],"supervision":[26],"signals":[27,132],"compress":[29],"contextual":[30],"information":[31],"into":[32,133],"representations.":[34],"However,":[35],"the":[36,40,83,106,111,127],"underlying":[37],"reasons":[38],"effectiveness":[41],"of":[42,51,86,113,130],"such":[43],"remain":[47],"unclear.":[48],"The":[49],"usage":[50],"Transformer-based":[53],"decoders":[54],"also":[55],"incurs":[56],"significant":[57],"computational":[58],"costs.":[59],"In":[60],"this":[61,69,99],"study,":[62],"we":[63,101],"aim":[64],"shed":[66],"light":[67],"on":[68,147],"issue":[70],"by":[71,109],"revealing":[72],"that":[73],"masked":[74,115,166],"(MAE)":[76],"with":[78,117,169],"enhanced":[79,170],"decoding":[80],"significantly":[81],"improves":[82],"term":[84],"coverage":[85],"input":[87],"tokens":[88],"in":[89],"representations,":[91],"compared":[92,163],"vanilla":[94],"BERT":[95],"checkpoints.":[96],"Building":[97],"upon":[98],"observation,":[100],"propose":[102],"modification":[104,125],"traditional":[107],"MAE":[108],"replacing":[110],"completely":[119],"simplified":[120],"Bag-of-Word":[121],"prediction":[122],"task.":[123],"This":[124],"enables":[126],"efficient":[128],"compression":[129],"lexical":[131],"representations":[135],"through":[136],"unsupervised":[137],"pre-training.":[138],"Remarkably,":[139],"our":[140],"proposed":[141],"method":[142],"achieves":[143],"state-of-the-art":[144],"performance":[146],"several":[148],"large-scale":[149],"benchmarks":[151],"without":[152],"requiring":[153],"any":[154],"parameters,":[156],"which":[157],"provides":[158],"67%":[160],"training":[161],"speed-up":[162],"standard":[165],"decoding.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}