{"id":"https://openalex.org/W7168402380","doi":"https://doi.org/10.1145/3805712.3809885","title":"PrepRet: Automated Data Preparation Pipeline Selection for Neural Retrieval","display_name":"PrepRet: Automated Data Preparation Pipeline Selection for Neural Retrieval","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168402380","doi":"https://doi.org/10.1145/3805712.3809885"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809885","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th 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/10.1145/3805712.3809885","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140881510","display_name":"Jing Chang","orcid":"https://orcid.org/0009-0004-8968-2972"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-8968-2972","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140800651","display_name":"Chang Liu","orcid":"https://orcid.org/0009-0003-7611-1735"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-7611-1735","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3642","last_page":"3646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6488000154495239},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.511900007724762},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4756999909877777},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3497999906539917},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.31029999256134033}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517799973487854},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.27790001034736633}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809885","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809885","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th 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":5,"referenced_works":["https://openalex.org/W2192203593","https://openalex.org/W3021397474","https://openalex.org/W3099700870","https://openalex.org/W3154670582","https://openalex.org/W4389520055"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"retrieval":[1,14,39],"models":[2],"typically":[3],"rely":[4],"on":[5,108,120],"fixed,":[6],"hand-crafted":[7],"preprocessing":[8,34,45,82],"pipelines":[9],"designed":[10],"independently":[11],"of":[12,64],"the":[13],"task,":[15],"leading":[16],"to":[17],"suboptimal":[18],"performance":[19],"that":[20,31],"varies":[21],"across":[22],"datasets":[23,111],"and":[24,37,72,97,122],"architectures.":[25],"We":[26,43],"propose":[27],"PrepRet,":[28],"a":[29,48,61],"framework":[30],"jointly":[32],"optimizes":[33],"pipeline":[35],"selection":[36,46,76],"neural":[38],"through":[40],"differentiable":[41,49],"optimization.":[42],"formulate":[44],"as":[47],"discrete":[50],"choice":[51],"problem":[52],"using":[53],"Gumbel-Softmax":[54],"relaxation,":[55],"enabling":[56],"end-to-end":[57],"gradient-based":[58],"learning":[59],"over":[60,92],"search":[62],"space":[63],"700":[65],"configurations":[66],"spanning":[67],"text":[68],"cleaning,":[69],"pre-tokenization,":[70],"chunking,":[71],"augmentation.":[73],"A":[74],"hierarchical":[75],"mechanism":[77],"captures":[78],"inter-stage":[79],"dependencies":[80],"between":[81],"operations.":[83],"On":[84],"MS":[85],"MARCO,":[86],"PrepRet":[87],"achieves":[88],"0.533":[89],"nDCG@10,":[90],"improving":[91],"Grid":[93],"Search":[94],"by":[95,99],"7.7%":[96],"Contriever":[98],"11.7%,":[100],"while":[101],"requiring":[102],"only":[103],"1.1":[104],"GPU-hours.":[105],"Zero-shot":[106],"evaluation":[107],"eight":[109],"BEIR":[110],"confirms":[112],"robust":[113],"cross-domain":[114],"generalization,":[115],"with":[116],"particularly":[117],"strong":[118],"gains":[119],"scientific":[121],"entity-rich":[123],"domains.":[124]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}