{"id":"https://openalex.org/W4385571010","doi":"https://doi.org/10.18653/v1/2023.acl-demo.57","title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","display_name":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385571010","doi":"https://doi.org/10.18653/v1/2023.acl-demo.57"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-demo.57","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.acl-demo.57","pdf_url":"https://aclanthology.org/2023.acl-demo.57.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-demo.57.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055847471","display_name":"Aleksandra Piktus","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Aleksandra Piktus","raw_affiliation_strings":["Sapienza University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013749071","display_name":"Odunayo Ogundepo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Odunayo Ogundepo","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033794353","display_name":"Christopher Akiki","orcid":"https://orcid.org/0000-0002-1634-5068","observed_orcids":["https://orcid.org/0000-0002-1634-5068"]},"institutions":[{"id":"https://openalex.org/I4401726909","display_name":"Center for Scalable Data Analytics and Artificial Intelligence","ror":"https://ror.org/01t4ttr56","country_code":"DE","type":"education","lineage":["https://openalex.org/I4401726909","https://openalex.org/I78650965","https://openalex.org/I926574661"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Akiki","raw_affiliation_strings":["Leipzig University","ScaDS . AI","ScaDS.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leipzig University","institution_ids":["https://openalex.org/I926574661"]},{"raw_affiliation_string":"ScaDS . AI","institution_ids":["https://openalex.org/I4401726909"]},{"raw_affiliation_string":"ScaDS.AI","institution_ids":["https://openalex.org/I4401726909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060546041","display_name":"Akintunde Oladipo","orcid":"https://orcid.org/0009-0000-2630-8167","observed_orcids":["https://orcid.org/0009-0000-2630-8167"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Akintunde Oladipo","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390744","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0009-0009-0756-8110","observed_orcids":["https://orcid.org/0009-0009-0756-8110"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080237064","display_name":"Hailey Schoelkopf","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hailey Schoelkopf","raw_affiliation_strings":["EleutherAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EleutherAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076733732","display_name":"Stella Biderman","orcid":"https://orcid.org/0000-0001-8228-1042","observed_orcids":["https://orcid.org/0000-0001-8228-1042"]},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stella Biderman","raw_affiliation_strings":["Booz Allen Hamilton","EleutherAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton","institution_ids":["https://openalex.org/I1322124587"]},{"raw_affiliation_string":"EleutherAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665","observed_orcids":["https://orcid.org/0000-0003-2451-0665"]},"institutions":[{"id":"https://openalex.org/I4401726909","display_name":"Center for Scalable Data Analytics and Artificial Intelligence","ror":"https://ror.org/01t4ttr56","country_code":"DE","type":"education","lineage":["https://openalex.org/I4401726909","https://openalex.org/I78650965","https://openalex.org/I926574661"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["Leipzig University","ScaDS . AI","ScaDS.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leipzig University","institution_ids":["https://openalex.org/I926574661"]},{"raw_affiliation_string":"ScaDS . AI","institution_ids":["https://openalex.org/I4401726909"]},{"raw_affiliation_string":"ScaDS.AI","institution_ids":["https://openalex.org/I4401726909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189","observed_orcids":["https://orcid.org/0000-0002-0661-7189"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055847471"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.1996,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39180848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6294000148773193,"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":0.6294000148773193,"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":0.17139999568462372,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.13729999959468842,"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/hugging-face","display_name":"Hugging Face","score":0.8790000081062317},{"id":"https://openalex.org/keywords/interoperability","display_name":"interoperability","score":0.699999988079071},{"id":"https://openalex.org/keywords/search-interfaces","display_name":"search interfaces","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696872889995575},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.6493015289306641},{"id":"https://openalex.org/C2776174103","wikidata":"https://www.wikidata.org/wiki/Q25339766","display_name":"STELLA (programming language)","level":2,"score":0.620969831943512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5660375356674194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5127037763595581},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45115363597869873},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4309615194797516},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43065983057022095},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29826438426971436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29472023248672485},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06944438815116882}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2023.acl-demo.57","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.acl-demo.57","pdf_url":"https://aclanthology.org/2023.acl-demo.57.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1717590","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1717590","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1717590/2/Piktus_GAIA_2023.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-demo.57","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.acl-demo.57","pdf_url":"https://aclanthology.org/2023.acl-demo.57.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385571010.pdf","grobid_xml":"https://content.openalex.org/works/W4385571010.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2342249984","https://openalex.org/W2512011479","https://openalex.org/W2593864460","https://openalex.org/W2740321901","https://openalex.org/W2948715311","https://openalex.org/W2989539713","https://openalex.org/W3001279689","https://openalex.org/W3003257820","https://openalex.org/W3099878876","https://openalex.org/W3102925513","https://openalex.org/W3118781290","https://openalex.org/W3133702157","https://openalex.org/W3137010024","https://openalex.org/W3158822421","https://openalex.org/W3162230617","https://openalex.org/W3180230246","https://openalex.org/W3197876970","https://openalex.org/W4221149706","https://openalex.org/W4221167110","https://openalex.org/W4224035735","https://openalex.org/W4225591000","https://openalex.org/W4226146865","https://openalex.org/W4226271314","https://openalex.org/W4226399820","https://openalex.org/W4226462293","https://openalex.org/W4229005866","https://openalex.org/W4229082214","https://openalex.org/W4281609260","https://openalex.org/W4281787103","https://openalex.org/W4283167130","https://openalex.org/W4284680984","https://openalex.org/W4288089799","https://openalex.org/W4306820534","https://openalex.org/W4310428868","https://openalex.org/W4312933868","https://openalex.org/W4322718191"],"related_works":["https://openalex.org/W196888113","https://openalex.org/W3212160542","https://openalex.org/W4238502331","https://openalex.org/W2984029695","https://openalex.org/W4241621507","https://openalex.org/W2798244240","https://openalex.org/W2464396084","https://openalex.org/W4391449271","https://openalex.org/W153512996","https://openalex.org/W2966736808"],"abstract_inverted_index":{"Aleksandra":[0],"Piktus,":[1],"Odunayo":[2],"Ogundepo,":[3],"Christopher":[4],"Akiki,":[5],"Akintunde":[6],"Oladipo,":[7],"Xinyu":[8],"Zhang,":[9],"Hailey":[10],"Schoelkopf,":[11],"Stella":[12],"Biderman,":[13],"Martin":[14],"Potthast,":[15],"Jimmy":[16],"Lin.":[17],"Proceedings":[18],"of":[19,24],"the":[20,25],"61st":[21],"Annual":[22],"Meeting":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"3:":[31],"System":[32],"Demonstrations).":[33],"2023.":[34]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-10-10T00:00:00"}