{"id":"https://openalex.org/W2251687356","doi":"https://doi.org/10.18653/v1/w15-4304","title":"Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text","display_name":"Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251687356","doi":"https://doi.org/10.18653/v1/w15-4304","mag":"2251687356"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-4304","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4304","pdf_url":"https://www.aclweb.org/anthology/W15-4304.pdf","source":null,"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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-4304.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026276934","display_name":"Marlies van der Wees","orcid":"https://orcid.org/0000-0003-1402-2764"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marlies van der Wees","raw_affiliation_strings":["Informatics Institute, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019968969","display_name":"Arianna Bisazza","orcid":"https://orcid.org/0000-0003-1270-3048"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arianna Bisazza","raw_affiliation_strings":["Informatics Institute, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109059955","display_name":"Christof Monz","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christof Monz","raw_affiliation_strings":["Informatics Institute, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"37"},"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":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9786999821662903,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8477041125297546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242834806442261},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7617608308792114},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6750773787498474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.624045193195343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6135400533676147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193299055099487},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5103954672813416},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4608786404132843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35901665687561035},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14354854822158813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09837251901626587}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8477041125297546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242834806442261},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7617608308792114},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6750773787498474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.624045193195343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6135400533676147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193299055099487},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5103954672813416},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4608786404132843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35901665687561035},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14354854822158813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09837251901626587},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w15-4304","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4304","pdf_url":"https://www.aclweb.org/anthology/W15-4304.pdf","source":null,"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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/d92206eb-2e58-4c76-956d-972f379f9e7f","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/five-shades-of-noise-analyzing-machine-translation-errors-in-usergenerated-text(d92206eb-2e58-4c76-956d-972f379f9e7f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"van der Wees, M, Bisazza, A & Monz, C 2015, Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text. in W Xu, B Han & A Ritter (eds), ACL-IJCNLP 2015 : ACL 2015 Workshop on Noisy User-generated Text : proceedings of the workshop : July 31, 2015, Beijing, China. Stroudsburg, PA, pp. 28-37, ACL 2015 Workshop on Noisy User-generated Text, 1/01/15. < http://www.aclweb.org/anthology/W/W15/W15-4304.pdf >","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/d92206eb-2e58-4c76-956d-972f379f9e7f","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/five-shades-of-noise-analyzing-machine-translation-errors-in-usergenerated-text(d92206eb-2e58-4c76-956d-972f379f9e7f).html","pdf_url":"http://www.aclweb.org/anthology/W/W15/W15-4304.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van der Wees, M, Bisazza, A & Monz, C 2015, Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text. in W Xu, B Han & A Ritter (eds), ACL-IJCNLP 2015 : ACL 2015 Workshop on Noisy User-generated Text : proceedings of the workshop : July 31, 2015, Beijing, China. Stroudsburg, PA, pp. 28-37, ACL 2015 Workshop on Noisy User-generated Text, 1/01/15. < http://www.aclweb.org/anthology/W/W15/W15-4304.pdf >","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/d92206eb-2e58-4c76-956d-972f379f9e7f","is_oa":false,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/five-shades-of-noise-analyzing-machine-translation-errors-in-usergenerated-text(d92206eb-2e58-4c76-956d-972f379f9e7f).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/w15-4304","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4304","pdf_url":"https://www.aclweb.org/anthology/W15-4304.pdf","source":null,"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 Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251687356.pdf","grobid_xml":"https://content.openalex.org/works/W2251687356.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1848260265","https://openalex.org/W1905522558","https://openalex.org/W1996456980","https://openalex.org/W2073805554","https://openalex.org/W2100976324","https://openalex.org/W2101105183","https://openalex.org/W2115056464","https://openalex.org/W2115410424","https://openalex.org/W2123301721","https://openalex.org/W2124769992","https://openalex.org/W2124807415","https://openalex.org/W2127876534","https://openalex.org/W2145685230","https://openalex.org/W2149327368","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2164806437","https://openalex.org/W2180952760","https://openalex.org/W2183189954","https://openalex.org/W2185701500","https://openalex.org/W2250293945","https://openalex.org/W2250952810","https://openalex.org/W2251202280","https://openalex.org/W2251784502","https://openalex.org/W2406343028","https://openalex.org/W2408655637","https://openalex.org/W2467575451","https://openalex.org/W2595715041","https://openalex.org/W3202724003","https://openalex.org/W3202971710","https://openalex.org/W4241645538"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W3037187668","https://openalex.org/W4362495644","https://openalex.org/W2962780935","https://openalex.org/W4234772502","https://openalex.org/W4387896177","https://openalex.org/W4385557855","https://openalex.org/W2807006873","https://openalex.org/W2883671469"],"abstract_inverted_index":{"It":[0],"is":[1,9],"widely":[2],"accepted":[3],"that":[4,98],"translating":[5],"usergenerated":[6],"(UG)":[7],"text":[8,47],"a":[10,58],"difficult":[11],"task":[12],"for":[13],"modern":[14],"statistical":[15],"machine":[16],"translation":[17,21,48,95,108],"(SMT)":[18],"systems.":[19],"The":[20,69],"quality":[22,33],"metrics":[23],"typically":[24],"used":[25],"in":[26,53],"the":[27,31,35,55,74,99],"SMT":[28,60,76,83,100],"literature":[29],"reflect":[30],"overall":[32],"of":[34,57,66,88,109],"system":[36,61],"output":[37],"but":[38],"provide":[39],"little":[40],"insight":[41],"into":[42],"what":[43],"exactly":[44],"makes":[45],"UG":[46,110],"difficult.":[49],"This":[50],"paper":[51],"analyzes":[52],"detail":[54],"behavior":[56],"state-of-the-art":[59],"on":[62],"five":[63],"different":[64],"types":[65],"informal":[67],"text.":[68],"results":[70],"help":[71],"to":[72,93,106],"demystify":[73],"poor":[75],"performance":[77],"experienced":[78],"by":[79],"researchers":[80],"who":[81],"use":[82],"as":[84],"an":[85],"intermediate":[86],"step":[87],"their":[89],"UG-NLP":[90],"pipeline,":[91],"and":[92],"identify":[94],"modeling":[96],"aspects":[97],"community":[101],"should":[102],"more":[103],"urgently":[104],"address":[105],"improve":[107],"data.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}