{"id":"https://openalex.org/W3083376297","doi":"https://doi.org/10.1145/3409256.3409836","title":"Sanitizing Synthetic Training Data Generation for Question Answering over Knowledge Graphs","display_name":"Sanitizing Synthetic Training Data Generation for Question Answering over Knowledge Graphs","publication_year":2020,"publication_date":"2020-09-05","ids":{"openalex":"https://openalex.org/W3083376297","doi":"https://doi.org/10.1145/3409256.3409836","mag":"3083376297"},"language":"en","primary_location":{"id":"doi:10.1145/3409256.3409836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409256.3409836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.04915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Trond Linjordet","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Trond Linjordet","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"last","author":{"id":null,"display_name":"Krisztian Balog","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Krisztian Balog","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92008406"],"apc_list":null,"apc_paid":null,"fwci":0.959,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81191507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.995199978351593,"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/question-answering","display_name":"Question answering","score":0.7583000063896179},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5766000151634216},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.510200023651123},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.47620001435279846},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4702000021934509},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4693000018596649},{"id":"https://openalex.org/keywords/experimental-data","display_name":"Experimental data","score":0.32359999418258667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3098999857902527}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7583000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084000110626221},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5060999989509583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4702000021934509},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3409256.3409836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409256.3409836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.04915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.04915","pdf_url":"https://arxiv.org/pdf/2009.04915","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.04915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.04915","pdf_url":"https://arxiv.org/pdf/2009.04915","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2126170172","https://openalex.org/W2149741699","https://openalex.org/W2159665776","https://openalex.org/W2251079237","https://openalex.org/W2566402689","https://openalex.org/W2591368218","https://openalex.org/W2759200442","https://openalex.org/W2763039547","https://openalex.org/W2883670913","https://openalex.org/W2915836468","https://openalex.org/W2919587621","https://openalex.org/W2949849869","https://openalex.org/W2954996726","https://openalex.org/W2962874939","https://openalex.org/W2963655793","https://openalex.org/W2963794306","https://openalex.org/W2964120615","https://openalex.org/W2964236999","https://openalex.org/W2970796366","https://openalex.org/W2971116243","https://openalex.org/W2980401255","https://openalex.org/W2988898811","https://openalex.org/W3015593590","https://openalex.org/W6739901393"],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"data":[1,21,47,74,93,105,134,165],"generation":[2,48,166],"is":[3,53,79,109],"important":[4],"to":[5,101,103,132],"training":[6],"and":[7,22,31,95,118,155],"evaluating":[8],"neural":[9],"models":[10,39,100,129],"for":[11,57],"question":[12,150],"answering":[13,151],"over":[14],"knowledge":[15],"graphs.":[16],"The":[17],"quality":[18],"of":[19,25,37,65,71,88,98,149,159],"the":[20,23,26,35,38,45,54,77,86,96,107,124,127,136,146],"partitioning":[24,78,138],"datasets":[27],"into":[28],"training,":[29],"validation":[30],"test":[32,104,133],"splits":[33,75],"impact":[34],"performance":[36],"trained":[40,99,128],"on":[41,50],"this":[42,58],"data.":[43],"If":[44],"synthetic":[46,164],"depends":[49],"templates,":[51],"as":[52],"predominant":[55],"approach":[56],"task,":[59],"there":[60],"may":[61],"be":[62],"a":[63,68,157],"leakage":[64,91,108,115],"information":[66,90,114],"via":[67],"shared":[69],"basis":[70],"templates":[72],"across":[73,92],"if":[76],"not":[80],"performed":[81],"hygienically.":[82],"This":[83],"paper":[84],"investigates":[85],"extent":[87],"such":[89],"splits,":[94],"ability":[97],"generalize":[102,131],"when":[106],"controlled.":[110],"We":[111],"find":[112],"that":[113,119,167],"indeed":[116],"occurs":[117],"it":[120],"affects":[121],"performance.":[122],"At":[123],"same":[125],"time,":[126],"do":[130],"under":[135],"sanitized":[137],"presented":[139],"here.":[140],"Importantly,":[141],"these":[142],"findings":[143],"extend":[144],"beyond":[145],"particular":[147],"flavor":[148],"task":[152],"we":[153],"studied":[154],"raise":[156],"series":[158],"difficult":[160],"questions":[161],"around":[162],"template-based":[163],"will":[168],"necessitate":[169],"additional":[170],"research.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2020-09-11T00:00:00"}