{"id":"https://openalex.org/W1982003829","doi":"https://doi.org/10.1109/slt.2012.6424200","title":"Crowdsourcing the acquisition of natural language corpora: Methods and observations","display_name":"Crowdsourcing the acquisition of natural language corpora: Methods and observations","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1982003829","doi":"https://doi.org/10.1109/slt.2012.6424200","mag":"1982003829"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100702485","display_name":"William Yang Wang","orcid":"https://orcid.org/0000-0001-6153-8240"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Yang Wang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research Redmond, WA 98052 U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research Redmond, WA 98052 U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030213540","display_name":"Dan Bohus","orcid":"https://orcid.org/0000-0002-6283-0590"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Bohus","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research Redmond, WA 98052 U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research Redmond, WA 98052 U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028114802","display_name":"Ece Kamar","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ece Kamar","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research Redmond, WA 98052 U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research Redmond, WA 98052 U.S.A","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043228682","display_name":"Eric Horvitz","orcid":"https://orcid.org/0000-0002-8823-0614"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Horvitz","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research Redmond, WA 98052 U.S.A"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research Redmond, WA 98052 U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100702485"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":6.9994,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96869229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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":0.9965000152587891,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.90916907787323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8839629888534546},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7697898149490356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7557604312896729},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6560438871383667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6507934927940369},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5598214864730835},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5568921566009521},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5113222599029541},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45495903491973877},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43060770630836487},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12837126851081848},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1067802906036377}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.90916907787323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8839629888534546},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7697898149490356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7557604312896729},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6560438871383667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6507934927940369},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5598214864730835},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5568921566009521},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5113222599029541},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45495903491973877},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43060770630836487},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12837126851081848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1067802906036377},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2012.6424200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.305.3995","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.305.3995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/people/horvitz/SLT_2012_crowdsourcing_natural_language.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3369151","https://openalex.org/W131533222","https://openalex.org/W159684104","https://openalex.org/W191512969","https://openalex.org/W1877590145","https://openalex.org/W1973200191","https://openalex.org/W2008127487","https://openalex.org/W2120589136","https://openalex.org/W2132232498","https://openalex.org/W2139448311","https://openalex.org/W2150514097","https://openalex.org/W2163361328","https://openalex.org/W2171144711","https://openalex.org/W4285719527","https://openalex.org/W6600124407","https://openalex.org/W6605323724","https://openalex.org/W6606481706","https://openalex.org/W6607704695","https://openalex.org/W6652326330","https://openalex.org/W6684172481"],"related_works":["https://openalex.org/W2367925007","https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2900126711","https://openalex.org/W4285240985","https://openalex.org/W4225162083","https://openalex.org/W3202115945","https://openalex.org/W2542958340","https://openalex.org/W4389520438"],"abstract_inverted_index":{"We":[0,53,74],"study":[1],"the":[2,59,64,71],"opportunity":[3],"for":[4,12,25,87],"using":[5],"crowdsourcing":[6,60],"methods":[7,24,38,83],"to":[8,32,42,84],"acquire":[9,85],"language":[10,16,28,89],"corpora":[11,86],"use":[13],"in":[14,80],"natural":[15,27,88],"processing":[17,90],"systems.":[18],"Specifically,":[19],"we":[20],"empirically":[21],"investigate":[22],"three":[23],"eliciting":[26],"sentences":[29],"that":[30],"correspond":[31],"a":[33],"given":[34],"semantic":[35,65],"form.":[36],"The":[37],"convey":[39],"frame":[40],"semantics":[41],"crowd":[43],"workers":[44],"by":[45],"means":[46],"of":[47,58,70],"sentences,":[48],"scenarios,":[49],"and":[50,62,68,78],"list-based":[51],"descriptions.":[52],"discuss":[54],"various":[55],"performance":[56],"measures":[57],"process,":[61],"analyze":[63],"correctness,":[66],"naturalness,":[67],"biases":[69],"collected":[72],"language.":[73],"highlight":[75],"research":[76],"challenges":[77],"directions":[79],"applying":[81],"these":[82],"applications.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}