{"id":"https://openalex.org/W2903253760","doi":"https://doi.org/10.18653/v1/w18-6483","title":"UTFPR at WMT 2018: Minimalistic Supervised Corpora Filtering for Machine Translation","display_name":"UTFPR at WMT 2018: Minimalistic Supervised Corpora Filtering for Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2903253760","doi":"https://doi.org/10.18653/v1/w18-6483","mag":"2903253760"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6483","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6483","pdf_url":"https://www.aclweb.org/anthology/W18-6483.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 Third Conference on Machine Translation: Shared Task Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6483.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103282283","display_name":"Gustavo Henrique Paetzold","orcid":"https://orcid.org/0000-0001-9951-050X"},"institutions":[{"id":"https://openalex.org/I59606676","display_name":"Universidade Federal do Par\u00e1","ror":"https://ror.org/03q9sr818","country_code":"BR","type":"education","lineage":["https://openalex.org/I59606676"]},{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Gustavo Paetzold","raw_affiliation_strings":["Federal University of Technology -Paran / Brazil","Federal University of Technology -Paran\u00e1 / Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Technology -Paran / Brazil","institution_ids":["https://openalex.org/I1283613182","https://openalex.org/I59606676"]},{"raw_affiliation_string":"Federal University of Technology -Paran\u00e1 / Brazil","institution_ids":["https://openalex.org/I1283613182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103282283"],"corresponding_institution_ids":["https://openalex.org/I1283613182","https://openalex.org/I59606676"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68815192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"923","last_page":"927"},"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":0.9994000196456909,"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":0.9922000169754028,"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":0.7804731130599976},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7396733164787292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6969355344772339},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5779911279678345},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5708668828010559},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5673718452453613},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5551497936248779},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5189076066017151},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.506041944026947},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.488844096660614},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4496595561504364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4016362428665161},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.15683934092521667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10555684566497803},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05386731028556824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804731130599976},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7396733164787292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6969355344772339},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5779911279678345},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5708668828010559},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5673718452453613},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5551497936248779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5189076066017151},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.506041944026947},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.488844096660614},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4496595561504364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4016362428665161},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.15683934092521667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10555684566497803},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05386731028556824},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6483","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6483","pdf_url":"https://www.aclweb.org/anthology/W18-6483.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 Third Conference on Machine Translation: Shared Task Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6483","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6483","pdf_url":"https://www.aclweb.org/anthology/W18-6483.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 Third Conference on Machine Translation: Shared Task Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903253760.pdf","grobid_xml":"https://content.openalex.org/works/W2903253760.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W630532510","https://openalex.org/W1499743609","https://openalex.org/W2133564696","https://openalex.org/W2419539795","https://openalex.org/W2508809683","https://openalex.org/W2595715041","https://openalex.org/W2760656271","https://openalex.org/W2806412155","https://openalex.org/W2903193068","https://openalex.org/W2963602293","https://openalex.org/W2963973721","https://openalex.org/W2964308564","https://openalex.org/W2964343359","https://openalex.org/W3025766093","https://openalex.org/W4298393544"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W2964083560","https://openalex.org/W3117807895"],"abstract_inverted_index":{"We":[0,56],"present":[1],"the":[2,6,63,82],"UTFPR":[3],"systems":[4],"at":[5],"WMT":[7],"2018":[8],"parallel":[9],"corpus":[10],"filtering":[11],"task.":[12],"Our":[13,66],"supervised":[14],"approach":[15],"discerns":[16],"between":[17],"good":[18],"and":[19,41],"bad":[20],"translations":[21,58],"by":[22,59],"training":[23],"classic":[24],"binary":[25,32],"classification":[26,33],"models":[27],"over":[28],"an":[29],"artificially":[30],"produced":[31],"dataset":[34],"derived":[35],"from":[36],"a":[37,42],"high-quality":[38],"translation":[39],"set,":[40],"minimalistic":[43],"set":[44],"of":[45],"6":[46],"semantic":[47],"distance":[48],"features":[49],"that":[50,69],"rely":[51],"only":[52],"on":[53],"easy-to-gather":[54],"resources.":[55],"rank":[57],"their":[60],"probability":[61],"for":[62],"\"good\"":[64],"label.":[65],"results":[67,80],"show":[68],"logistic":[70],"regression":[71],"pairs":[72],"best":[73],"with":[74],"our":[75],"approach,":[76],"yielding":[77],"more":[78],"consistent":[79],"throughout":[81],"different":[83],"settings":[84],"evaluated.":[85]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}