{"id":"https://openalex.org/W2970810395","doi":"https://doi.org/10.3390/informatics6030035","title":"Misalignment Detection for Web-Scraped Corpora: A Supervised Regression Approach","display_name":"Misalignment Detection for Web-Scraped Corpora: A Supervised Regression Approach","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2970810395","doi":"https://doi.org/10.3390/informatics6030035","mag":"2970810395"},"language":"en","primary_location":{"id":"doi:10.3390/informatics6030035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics6030035","pdf_url":"https://www.mdpi.com/2227-9709/6/3/35/pdf?version=1568797156","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2227-9709/6/3/35/pdf?version=1568797156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033665514","display_name":"Arne Defauw","orcid":"https://orcid.org/0000-0003-1946-9178"},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Arne Defauw","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043461691","display_name":"Sara Szoc","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sara Szoc","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000963686","display_name":"Anna Bardadym","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Anna Bardadym","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059521831","display_name":"Joris Brabers","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Joris Brabers","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018341634","display_name":"Frederic Everaert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Frederic Everaert","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096795279","display_name":"Roko Mijic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roko Mijic","raw_affiliation_strings":["Independent Data Science Consultant, 9000 Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"Independent Data Science Consultant, 9000 Ghent, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051271245","display_name":"Kim Scholte","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kim Scholte","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002121250","display_name":"Tom Vanallemeersch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tom Vanallemeersch","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035718753","display_name":"Koen Van Winckel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Koen Van Winckel","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020047146","display_name":"Joachim Van den Bogaert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103630","display_name":"CrossLang (Belgium)","ror":"https://ror.org/01dpfdz03","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210103630"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Joachim Van den Bogaert","raw_affiliation_strings":["CrossLang NV, 9050 Gentbrugge, Belgium"],"affiliations":[{"raw_affiliation_string":"CrossLang NV, 9050 Gentbrugge, Belgium","institution_ids":["https://openalex.org/I4210103630"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5033665514"],"corresponding_institution_ids":["https://openalex.org/I4210103630"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.14,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56629399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":"3","first_page":"35","last_page":"35"},"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":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.9976999759674072,"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":0.8263682126998901},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7599594593048096},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6447230577468872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6436653137207031},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5655975341796875},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5470702052116394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5099409818649292},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.49595507979393005},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48233577609062195},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47100865840911865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4128953814506531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3714064657688141},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07190319895744324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263682126998901},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7599594593048096},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6447230577468872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6436653137207031},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5655975341796875},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5470702052116394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5099409818649292},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.49595507979393005},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48233577609062195},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47100865840911865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4128953814506531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3714064657688141},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07190319895744324},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/informatics6030035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics6030035","pdf_url":"https://www.mdpi.com/2227-9709/6/3/35/pdf?version=1568797156","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2442fc86137a448db0a3d4a8d3d99a98","is_oa":true,"landing_page_url":"https://doaj.org/article/2442fc86137a448db0a3d4a8d3d99a98","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Informatics, Vol 6, Iss 3, p 35 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2227-9709/6/3/35/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/informatics6030035","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Informatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/informatics6030035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics6030035","pdf_url":"https://www.mdpi.com/2227-9709/6/3/35/pdf?version=1568797156","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970810395.pdf","grobid_xml":"https://content.openalex.org/works/W2970810395.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1973152633","https://openalex.org/W2101234009","https://openalex.org/W2107695330","https://openalex.org/W2117652747","https://openalex.org/W2496235729","https://openalex.org/W2513660799","https://openalex.org/W2572136474","https://openalex.org/W2609278920","https://openalex.org/W2739740656","https://openalex.org/W2741900445","https://openalex.org/W2742155240","https://openalex.org/W2767899794","https://openalex.org/W2794607286","https://openalex.org/W2798389157","https://openalex.org/W2805411799","https://openalex.org/W2807849360","https://openalex.org/W2886198413","https://openalex.org/W2890095519","https://openalex.org/W2899337869","https://openalex.org/W2902918014","https://openalex.org/W2903035303","https://openalex.org/W2962735107","https://openalex.org/W2963212250","https://openalex.org/W2963918774","https://openalex.org/W2963919854","https://openalex.org/W2964022663","https://openalex.org/W2978660557","https://openalex.org/W3166956191","https://openalex.org/W3208011254","https://openalex.org/W4322800759","https://openalex.org/W6675354045","https://openalex.org/W6723821839","https://openalex.org/W6731807709"],"related_works":["https://openalex.org/W2575897682","https://openalex.org/W2081797125","https://openalex.org/W2996079066","https://openalex.org/W1967312449","https://openalex.org/W1986094003","https://openalex.org/W3092043337","https://openalex.org/W2096044998","https://openalex.org/W1424383737","https://openalex.org/W2728761353","https://openalex.org/W2883671469"],"abstract_inverted_index":{"To":[0],"build":[1],"state-of-the-art":[2],"Neural":[3],"Machine":[4],"Translation":[5],"(NMT)":[6],"systems,":[7],"high-quality":[8],"parallel":[9],"sentences":[10,73],"are":[11,18],"needed.":[12],"Typically,":[13],"large":[14],"amounts":[15],"of":[16,36,42,66,71,133,148,165,186],"data":[17],"scraped":[19],"from":[20],"multilingual":[21],"web":[22],"sites":[23],"and":[24,102,120,136],"aligned":[25,45,72],"into":[26],"datasets":[27],"for":[28,33,57,145,154],"training.":[29],"Many":[30],"tools":[31],"exist":[32],"automatic":[34,58],"alignment":[35],"such":[37],"datasets.":[38],"However,":[39],"the":[40,43,64,93,114,118,121,127,134,137,140,146,163,184],"quality":[41,164],"resulting":[44],"corpus":[46,169],"can":[47,161],"be":[48],"disappointing.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,156,178],"present":[54],"a":[55,69,75,79,88,168,172],"tool":[56,181],"misalignment":[59,149],"detection":[60],"(MAD).":[61],"We":[62,83,110],"treated":[63],"task":[65,147],"determining":[67],"whether":[68],"pair":[70],"constitutes":[74],"genuine":[76],"translation":[77,108],"as":[78,124,126],"supervised":[80],"regression":[81],"problem.":[82],"trained":[84],"our":[85,159,180],"algorithm":[86,98],"on":[87,188],"manually":[89],"labeled":[90],"dataset":[91],"in":[92,167],"FR\u2013NL":[94],"language":[95],"pair.":[96],"Our":[97],"used":[99,179],"shallow":[100],"features":[101,103,144],"obtained":[104],"after":[105],"an":[106],"initial":[107],"step.":[109],"showed":[111],"that":[112,158],"both":[113],"Levenshtein":[115],"distance":[116,129],"between":[117,130],"target":[119,138],"translated":[122],"source,":[123],"well":[125],"cosine":[128],"sentence":[131],"embeddings":[132],"source":[135],"were":[139],"two":[141],"most":[142],"important":[143],"detection.":[150],"Using":[151],"gold":[152],"standards":[153],"alignment,":[155],"demonstrated":[157],"model":[160],"increase":[162],"alignments":[166],"substantially,":[170],"reaching":[171],"precision":[173],"close":[174],"to":[175,182],"100%.":[176],"Finally,":[177],"investigate":[183],"effect":[185],"misalignments":[187],"NMT":[189],"performance.":[190]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
