{"id":"https://openalex.org/W7157133462","doi":"https://doi.org/10.48550/arxiv.2604.22758","title":"RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching","display_name":"RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching","publication_year":2026,"publication_date":"2026-03-07","ids":{"openalex":"https://openalex.org/W7157133462","doi":"https://doi.org/10.48550/arxiv.2604.22758"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22758","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.22758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134788939","display_name":"Tong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134806446","display_name":"Yongqin Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yongqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134802985","display_name":"Jianfeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108965069","display_name":"Lingxi Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Lingxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063775146","display_name":"Wenqing Wei","orcid":"https://orcid.org/0009-0001-5421-0316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Wenqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023161786","display_name":"\u9648\u82cf\u5dde","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Suzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134804175","display_name":"Huan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134765259","display_name":"Ke Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134771019","display_name":"Lidan Shou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shou, Lidan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.314300000667572,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.314300000667572,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.21559999883174896,"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":0.15610000491142273,"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/word-embedding","display_name":"Word embedding","score":0.5275999903678894},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5242000222206116},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4690000116825104},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4255000054836273},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.37700000405311584},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.3244999945163727},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.3221000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885999917984009},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5275999903678894},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C37952496","wikidata":"https://www.wikidata.org/wiki/Q5001829","display_name":"Business analytics","level":4,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22758","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.22758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22758","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"at":[1],"Xiaohongshu,":[2],"the":[3,86,98],"rapid":[4],"expansion":[5],"of":[6],"e-commerce":[7],"and":[8,17,42,59,89,112,141,173,186],"advertising":[9],"demands":[10],"real-time":[11],"business":[12],"analytics":[13],"with":[14],"high":[15,57,87],"accuracy":[16,176,190],"low":[18],"latency.":[19],"To":[20],"meet":[21],"this":[22,50,69],"demand,":[23],"systems":[24],"typically":[25],"rely":[26],"on":[27,159,179],"converting":[28],"natural":[29],"language":[30],"(NL)":[31],"queries":[32],"into":[33],"Domain-Specific":[34],"Languages":[35],"(DSLs)":[36],"to":[37,154],"ensure":[38],"semantic":[39,83],"consistency,":[40],"validation,":[41],"portability.":[43],"However,":[44],"existing":[45],"multi-stage":[46],"LLM":[47],"pipelines":[48],"for":[49,65,138],"NL-to-DSL":[51,76],"task":[52],"suffer":[53],"from":[54,164,184],"prohibitive":[55],"latency,":[56],"cost,":[58],"error":[60],"propagation,":[61],"rendering":[62],"them":[63],"unsuitable":[64],"enterprise-scale":[66],"deployment.":[67],"In":[68],"paper,":[70],"we":[71],"propose":[72],"RedParrot,":[73],"a":[74,82,143],"novel":[75],"framework":[77],"that":[78,149],"accelerates":[79],"inference":[80],"via":[81,135],"cache.":[84],"Observing":[85],"repetition":[88],"stable":[90],"structural":[91,110],"patterns":[92],"in":[93],"user":[94],"queries,":[95],"RedParrot":[96,167],"bypasses":[97],"costly":[99],"pipeline":[100],"by":[101,191],"matching":[102],"new":[103,180],"requests":[104],"against":[105],"cached":[106],"\"query":[107],"skeletons\"":[108],"(normalized":[109],"patterns)":[111],"adapting":[113],"their":[114],"corresponding":[115],"DSLs.":[116],"Our":[117],"core":[118],"technical":[119],"contributions":[120],"include":[121],"(1)":[122],"an":[123,129,169,174],"offline":[124],"skeleton":[125],"construction":[126],"strategy,":[127],"(2)":[128],"online,":[130],"entity-agnostic":[131],"embedding":[132],"model":[133],"trained":[134],"contrastive":[136],"learning":[137,197],"robust":[139],"matching,":[140],"(3)":[142],"heterogeneous":[144],"Retrieval-Augmented":[145],"Generation":[146],"(RAG)":[147],"method":[148],"integrates":[150],"diverse":[151],"knowledge":[152],"sources":[153],"handle":[155],"unseen":[156],"entities.":[157],"Experiments":[158],"six":[160],"real":[161],"enterprise":[162],"datasets":[163],"Xiaohongshu":[165],"show":[166],"achieves":[168],"average":[170],"3.6x":[171],"speedup":[172],"8.26%":[175],"improvement.":[177],"Furthermore,":[178],"public":[181],"benchmarks":[182],"adapted":[183],"Spider":[185],"BIRD,":[187],"it":[188],"boosts":[189],"34.8%,":[192],"substantially":[193],"outperforming":[194],"standard":[195],"in-context":[196],"baselines.":[198]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-29T00:00:00"}