{"id":"https://openalex.org/W2058867523","doi":"https://doi.org/10.1109/icassp.2013.6639305","title":"Statistical machine translation based text normalization with crowdsourcing","display_name":"Statistical machine translation based text normalization with crowdsourcing","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2058867523","doi":"https://doi.org/10.1109/icassp.2013.6639305","mag":"2058867523"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5019720894","display_name":"Tim Schlippe","orcid":"https://orcid.org/0000-0002-9462-8610"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Schlippe","raw_affiliation_strings":["Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066247121","display_name":"Chenfei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chenfei Zhu","raw_affiliation_strings":["Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001202948","display_name":"Daniel Lemcke","orcid":"https://orcid.org/0000-0001-5683-2197"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Lemcke","raw_affiliation_strings":["Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Systems Laboratory, Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.9887,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82721772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8406","last_page":"8410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8583564162254333},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7568731307983398},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.740043580532074},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7261630296707153},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6906513571739197},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6591504216194153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5903576612472534},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.47347986698150635},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44644874334335327},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4308868944644928},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41117367148399353},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27143043279647827},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07897889614105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583564162254333},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7568731307983398},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.740043580532074},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7261630296707153},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6906513571739197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6591504216194153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5903576612472534},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.47347986698150635},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44644874334335327},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4308868944644928},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41117367148399353},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27143043279647827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07897889614105225},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1445196116","https://openalex.org/W1507805082","https://openalex.org/W1522352264","https://openalex.org/W1631260214","https://openalex.org/W2018616927","https://openalex.org/W2053966956","https://openalex.org/W2057900969","https://openalex.org/W2104499423","https://openalex.org/W2104907655","https://openalex.org/W2114269021","https://openalex.org/W2124807415","https://openalex.org/W2127849236","https://openalex.org/W2144226312","https://openalex.org/W2156985047","https://openalex.org/W2163942301","https://openalex.org/W2288542159","https://openalex.org/W6628418794","https://openalex.org/W6630380851","https://openalex.org/W6636811518","https://openalex.org/W6675506178","https://openalex.org/W6675631943","https://openalex.org/W6681468851"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W2604275745","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W2985215540","https://openalex.org/W4307459710","https://openalex.org/W3155572818","https://openalex.org/W4293584592","https://openalex.org/W3023559046"],"abstract_inverted_index":{"In":[0,67],"[1],":[1],"we":[2,70,78,109],"have":[3,135],"proposed":[4],"systems":[5],"for":[6,74,84],"text":[7,34],"normalization":[8],"based":[9],"on":[10],"statistical":[11],"machine":[12],"translation":[13],"(SMT)":[14],"methods":[15],"which":[16,134],"are":[17,59],"constructed":[18],"with":[19,28],"the":[20,80,93,106,114,124,132],"support":[21],"of":[22,49,95],"Internet":[23,31],"users":[24,32],"and":[25,51,91],"evaluated":[26],"those":[27,103],"French":[29],"texts.":[30],"normalize":[33],"displayed":[35],"in":[36,40,87,99],"a":[37,46],"web":[38],"interface":[39],"an":[41,120],"annotation":[42,82],"process,":[43],"thereby":[44],"providing":[45],"parallel":[47],"corpus":[48],"normalized":[50,65],"non-normalized":[52,63],"text.":[53,66],"With":[54],"this":[55,68],"corpus,":[56],"SMT":[57,121],"models":[58],"generated":[60],"to":[61,102,112,123,127],"translate":[62],"into":[64],"paper,":[69],"analyze":[71],"their":[72],"efficiency":[73],"other":[75],"languages.":[76],"Additionally,":[77],"embedded":[79],"English":[81],"process":[83],"training":[85],"data":[86],"Amazon":[88],"Mechanical":[89],"Turk":[90],"compare":[92],"quality":[94],"texts":[96],"thoroughly":[97],"annotated":[98,104,137],"our":[100],"lab":[101],"by":[105,117],"Turkers.":[107],"Finally,":[108],"investigate":[110],"how":[111],"reduce":[113],"user":[115],"effort":[116],"iteratively":[118],"applying":[119],"system":[122],"next":[125],"sentences":[126,133],"be":[128],"edited,":[129],"built":[130],"from":[131],"been":[136],"so":[138],"far.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}