{"id":"https://openalex.org/W7126387156","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.81","title":"Exploring efficient zero-shot synthetic dataset generation for Information Retrieval","display_name":"Exploring efficient zero-shot synthetic dataset generation for Information Retrieval","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126387156","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.81"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.81","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.81","pdf_url":"https://aclanthology.org/2024.findings-eacl.81.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.81.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124598111","display_name":"Tiago Almeida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiago Almeida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073280030","display_name":"S\u00e9rgio Matos","orcid":"https://orcid.org/0000-0003-1941-3983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9rgio Matos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68710377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1214","last_page":"1231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07259999960660934,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07259999960660934,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0697999969124794,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03970000147819519,"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/document-retrieval","display_name":"Document retrieval","score":0.33180001378059387},{"id":"https://openalex.org/keywords/data-retrieval","display_name":"Data retrieval","score":0.32109999656677246},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26669999957084656},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.266400009393692},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.2628999948501587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6425999999046326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41510000824928284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.81","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.81","pdf_url":"https://aclanthology.org/2024.findings-eacl.81.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.81","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.81","pdf_url":"https://aclanthology.org/2024.findings-eacl.81.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6147775995","display_name":"Institute of Electronics and Informatics Engineering of Aveiro","funder_award_id":"UIDB/00127/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126387156.pdf","grobid_xml":"https://content.openalex.org/works/W7126387156.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"broad":[1],"integration":[2],"of":[3,27,54,100,137,147,171],"neural":[4,66,81,172],"retrieval":[5,67,152],"models":[6,57,83],"into":[7],"Information":[8],"Retrieval":[9],"(IR)":[10],"systems":[11],"is":[12,90,177],"significantly":[13],"impeded":[14],"by":[15,129],"the":[16,24,44,52,98,105,135,145],"high":[17],"cost":[18],"and":[19,157],"laborious":[20],"process":[21],"associated":[22],"with":[23],"manual":[25],"labelling":[26],"training":[28,31,80,170],"data.Similarly,":[29],"synthetic":[30,62,77],"data":[32,89],"generation,":[33,127],"a":[34,93,119,130],"potential":[35,53,146],"workaround,":[36],"often":[37],"requires":[38],"expensive":[39],"computational":[40],"resources":[41],"due":[42],"to":[43,64,70,75,103,109,133],"reliance":[45],"on":[46,141],"large":[47],"language":[48,56,121],"models.This":[49],"work":[50],"explored":[51],"small":[55,120],"for":[58,114,123],"efficiently":[59,164],"creating":[60],"high-quality":[61],"datasets":[63,143],"train":[65],"models.We":[68],"aim":[69],"identify":[71],"an":[72,163],"optimal":[73],"method":[74],"generate":[76],"datasets,":[78],"enabling":[79],"reranking":[82],"in":[84,97,174],"document":[85],"collections":[86],"where":[87],"annotated":[88],"unavailable.We":[91],"introduce":[92],"novel":[94],"methodology,":[95],"grounded":[96],"principles":[99],"information":[101],"theory,":[102],"select":[104],"most":[106],"appropriate":[107],"documents":[108],"be":[110],"used":[111],"as":[112,155],"context":[113],"question":[115,126],"generation.Then,":[116],"we":[117],"employ":[118],"model":[122],"zero-shot":[124],"conditional":[125],"supplemented":[128],"filtering":[131],"mechanism":[132],"ensure":[134],"quality":[136],"generated":[138,165],"questions.Extensive":[139],"evaluation":[140],"five":[142],"unveils":[144],"our":[148],"approach,":[149],"outperforming":[150],"unsupervised":[151],"methods":[153],"such":[154],"BM25":[156],"pretrained":[158],"monoT5.Our":[159],"findings":[160],"indicate":[161],"that":[162],"\"silver-standard\"":[166],"dataset":[167],"allows":[168],"effective":[169],"rerankers":[173],"unlabeled":[175],"scenarios.Code":[176],"publicly":[178],"available":[179],"at":[180],"https://github.com/ieeta-pt/SynQGen.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}