{"id":"https://openalex.org/W3120697923","doi":"https://doi.org/10.18653/v1/2020.wmt-1.105","title":"Filtering Noisy Parallel Corpus using Transformers with Proxy Task Learning","display_name":"Filtering Noisy Parallel Corpus using Transformers with Proxy Task Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3120697923","doi":"https://doi.org/10.18653/v1/2020.wmt-1.105","mag":"3120697923"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.105","pdf_url":"https://aclanthology.org/2020.wmt-1.105.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.105.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016655666","display_name":"Haluk A\u00e7ar\u00e7i\u00e7ek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haluk A\u00e7ar\u00e7i\u00e7ek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069570906","display_name":"Talha \u00c7olako\u011flu","orcid":"https://orcid.org/0000-0002-4524-862X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talha \u00c7olako\u011flu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090850007","display_name":"P\u0131nar Ece Aktan Hatipo\u011flu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P\u0131nar Ece Aktan Hatipo\u011flu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036059435","display_name":"Chong Hsuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Hsuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701893","display_name":"Wei Peng","orcid":"https://orcid.org/0000-0001-8179-1577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.575,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71391723,"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":"940","last_page":"946"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9916999936103821,"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":0.8651576042175293},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7027338743209839},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6052974462509155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6028251647949219},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5850925445556641},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5428575873374939},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5040653944015503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4676232933998108},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4538976848125458},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4227878451347351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32128530740737915},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1014007031917572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8651576042175293},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7027338743209839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6052974462509155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6028251647949219},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5850925445556641},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5428575873374939},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5040653944015503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4676232933998108},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4538976848125458},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4227878451347351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32128530740737915},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1014007031917572},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.105","pdf_url":"https://aclanthology.org/2020.wmt-1.105.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"mag:3120697923","is_oa":false,"landing_page_url":"https://aclanthology.org/2020.wmt-1.105/","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.105","pdf_url":"https://aclanthology.org/2020.wmt-1.105.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3120697923.pdf","grobid_xml":"https://content.openalex.org/works/W3120697923.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1905522558","https://openalex.org/W2886198413","https://openalex.org/W2962696263","https://openalex.org/W2963281280","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2970686691","https://openalex.org/W2970858854","https://openalex.org/W2971045947","https://openalex.org/W2983040767","https://openalex.org/W3015018381","https://openalex.org/W3031484690","https://openalex.org/W3107826490"],"related_works":["https://openalex.org/W2949271546","https://openalex.org/W1895614922","https://openalex.org/W2970229707","https://openalex.org/W3172547746","https://openalex.org/W2892375082","https://openalex.org/W3139630677","https://openalex.org/W2781611779","https://openalex.org/W2738452268","https://openalex.org/W3207606154","https://openalex.org/W2983785000","https://openalex.org/W2982115308","https://openalex.org/W3194607125","https://openalex.org/W3098382480","https://openalex.org/W3199135883","https://openalex.org/W2946423414","https://openalex.org/W3089596261","https://openalex.org/W2949135528","https://openalex.org/W2951805270","https://openalex.org/W2980629466","https://openalex.org/W3127853158"],"abstract_inverted_index":{"This":[0],"paper":[1,84],"illustrates":[2],"Huawei's":[3],"submission":[4],"to":[5,31,46,59],"the":[6,33,61,68,77],"WMT20":[7],"low-resource":[8],"parallel":[9,38],"corpus":[10],"filtering":[11,34],"shared":[12],"task.Our":[13],"approach":[14,74],"focuses":[15],"on":[16,22],"developing":[17],"a":[18,25,40,88],"proxy":[19],"task":[20,42],"learner":[21],"top":[23],"of":[24,67,90],"transformer-based":[26],"multilingual":[27],"pre-trained":[28],"language":[29],"model":[30],"boost":[32],"capability":[35],"for":[36,96],"noisy":[37],"corpora.Such":[39],"supervised":[41],"also":[43],"helps":[44],"us":[45],"iterate":[47],"much":[48],"more":[49],"quickly":[50],"than":[51],"using":[52],"an":[53],"existing":[54],"neural":[55],"machine":[56],"translation":[57],"system":[58],"perform":[60],"same":[62],"task.After":[63],"performing":[64],"empirical":[65],"analyses":[66],"finetuning":[69],"task,":[70],"we":[71],"benchmark":[72],"our":[73],"by":[75],"comparing":[76],"results":[78],"with":[79,87],"past":[80],"years'":[81],"state-of-theart":[82],"records.This":[83],"wraps":[85],"up":[86],"discussion":[89],"limitations":[91],"and":[92],"future":[93],"work.The":[94],"scripts":[95],"this":[97],"study":[98],"will":[99],"be":[100],"made":[101],"publicly":[102],"available.":[103]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2021-01-18T00:00:00"}