{"id":"https://openalex.org/W2104907655","doi":null,"title":"Can Crowds Build parallel corpora for Machine Translation Systems","display_name":"Can Crowds Build parallel corpora for Machine Translation Systems","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2104907655","mag":"2104907655"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.168.3907","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.168.3907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Evamshi/publications/mturk_naacl.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5055725235","display_name":"Vamshi Ambati","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamshi Ambati","raw_affiliation_strings":["Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064572063","display_name":"Stephan Vogel","orcid":"https://orcid.org/0000-0003-2630-4881","observed_orcids":["https://orcid.org/0000-0003-2630-4881"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Vogel","raw_affiliation_strings":["Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":"https://orcid.org/0000-0003-2630-4881","affiliations":[{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":7.2485,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97187483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T10759","display_name":"Translation Studies and Practices","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-corpus-construction","display_name":"parallel corpus construction","score":0.7739999890327454},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"crowdsourcing","score":0.9340000152587891},{"id":"https://openalex.org/keywords/mechanical-turk","display_name":"Mechanical Turk","score":0.9470000267028809},{"id":"https://openalex.org/keywords/sentence-translation","display_name":"sentence translation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/phrase-translation","display_name":"phrase translation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/context-sensitive-translation","display_name":"context-sensitive translation","score":0.5630000233650208},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8824776411056519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8777714967727661},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7400938272476196},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6939483284950256},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6688014268875122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6660561561584473},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6529015302658081},{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.6342984437942505},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6099814176559448},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.603050947189331},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5867529511451721},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5249971151351929},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.5018672943115234},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.48411428928375244},{"id":"https://openalex.org/C110046852","wikidata":"https://www.wikidata.org/wiki/Q468495","display_name":"Computer-assisted translation","level":3,"score":0.4697069823741913},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.4289812445640564},{"id":"https://openalex.org/C51802942","wikidata":"https://www.wikidata.org/wiki/Q7662211","display_name":"Synchronous context-free grammar","level":4,"score":0.42350202798843384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05034840106964111},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.168.3907","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.168.3907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Evamshi/publications/mturk_naacl.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.9141","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.9141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/W/W10/W10-0710.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.631.2878","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.631.2878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/NAACL-HLT-2010-Ambati.pdf","raw_type":"text"},{"id":"mag:2104907655","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/W10-0710/","pdf_url":null,"source":{"id":"https://openalex.org/S4306420633","display_name":"North American Chapter of the Association for Computational Linguistics","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"North American Chapter of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W229329885","https://openalex.org/W1522553155","https://openalex.org/W1970381522","https://openalex.org/W2124807415","https://openalex.org/W2133512280","https://openalex.org/W2143539737"],"related_works":["https://openalex.org/W170711724","https://openalex.org/W2164479068","https://openalex.org/W2107695330","https://openalex.org/W7100393243","https://openalex.org/W2185853379","https://openalex.org/W2250338219","https://openalex.org/W2251339511","https://openalex.org/W7046929794","https://openalex.org/W7095616597","https://openalex.org/W6908106033"],"abstract_inverted_index":{"Corpus":[0],"based":[1],"approaches":[2],"to":[3,58],"machine":[4],"transla-tion":[5],"(MT)":[6],"rely":[7],"on":[8],"the":[9,19,30,48,59,67,70],"availability":[10],"of":[11,21,32,39,50,69],"parallel":[12],"corpora.":[13,27],"In":[14],"this":[15],"paper":[16],"we":[17],"explore":[18,29],"effec-tiveness":[20],"Mechanical":[22],"Turk":[23],"for":[24,47,61],"creating":[25],"par-allel":[26],"We":[28,42],"task":[31,49],"sen-tence":[33],"translation,":[34,52],"both":[35],"into":[36],"and":[37,65],"out":[38],"a":[40],"lan-guage.":[41],"also":[43],"perform":[44],"preliminary":[45],"experi-ments":[46],"phrase":[51],"where":[53],"ambiguous":[54],"phrases":[55],"are":[56],"provided":[57],"turker":[60],"translation":[62],"in":[63,66],"isolation":[64],"context":[68],"sentence":[71],"it":[72],"originated":[73],"from.":[74],"1":[75]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":10}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
