{"id":"https://openalex.org/W3119453866","doi":"https://doi.org/10.18653/v1/w18-6482","title":"Alibaba Submission to the WMT18 Parallel Corpus Filtering Task","display_name":"Alibaba Submission to the WMT18 Parallel Corpus Filtering Task","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W3119453866","doi":"https://doi.org/10.18653/v1/w18-6482","mag":"3119453866"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6482","pdf_url":"https://www.aclweb.org/anthology/W18-6482.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/W18-6482.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031497022","display_name":"Jun Lu","orcid":"https://orcid.org/0000-0002-2853-427X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lu","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006872434","display_name":"Xiaoyu Lv","orcid":"https://orcid.org/0000-0001-5706-410X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Lv","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037003444","display_name":"Yangbin Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangbin Shi","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019715118","display_name":"Boxing Chen","orcid":"https://orcid.org/0000-0002-3170-4858"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boxing Chen","raw_affiliation_strings":["Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology Lab, Alibaba Group Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019715118"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":1.5188,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87663823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"917","last_page":"922"},"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":0.9970999956130981,"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":0.8654704689979553},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7687045335769653},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7365442514419556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7347097396850586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6447464823722839},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.6375682353973389},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6294381022453308},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5156934857368469},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5139064788818359},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45587295293807983},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3649945855140686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8654704689979553},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7687045335769653},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7365442514419556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7347097396850586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6447464823722839},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6375682353973389},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6294381022453308},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5156934857368469},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5139064788818359},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45587295293807983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3649945855140686},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w18-6482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6482","pdf_url":"https://www.aclweb.org/anthology/W18-6482.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"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:6a17ac14-d76b-4b32-9343-93b03c77ca0d","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=6a17ac14-d76b-4b32-9343-93b03c77ca0d","pdf_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=6a17ac14-d76b-4b32-9343-93b03c77ca0d","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6482","pdf_url":"https://www.aclweb.org/anthology/W18-6482.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":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3119453866.pdf","grobid_xml":"https://content.openalex.org/works/W3119453866.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1560797130","https://openalex.org/W1834000468","https://openalex.org/W2101105183","https://openalex.org/W2108459463","https://openalex.org/W2117278770","https://openalex.org/W2123318312","https://openalex.org/W2141440284","https://openalex.org/W2148708890","https://openalex.org/W2251453970","https://openalex.org/W2399188371","https://openalex.org/W2523478734","https://openalex.org/W2758884106","https://openalex.org/W2903297715","https://openalex.org/W2963281280","https://openalex.org/W2963506925","https://openalex.org/W2963919854","https://openalex.org/W2970686691","https://openalex.org/W3208011254","https://openalex.org/W4298393544"],"related_works":["https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W2990400634","https://openalex.org/W2794347674","https://openalex.org/W2797913374","https://openalex.org/W2121870595","https://openalex.org/W2604275745","https://openalex.org/W2986030184"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,10,21,24,27,31,37,41,46,58],"Alibaba":[4],"Machine":[5],"Translation":[6],"Group":[7],"submissions":[8],"to":[9,56,71,75],"WMT":[11],"2018":[12],"Shared":[13],"Task":[14],"on":[15],"Parallel":[16],"Corpus":[17],"Filtering.":[18],"While":[19],"evaluating":[20],"quality":[22,43],"of":[23,30],"parallel":[25,59,64],"corpus,":[26],"three":[28],"characteristics":[29],"corpus":[32,47,65],"are":[33,54],"investigated,":[34],"i.e.":[35],"1)":[36],"bilingual/translation":[38],"quality,":[39],"2)":[40],"monolingual":[42],"and":[44,51,73],"3)":[45],"diversity.":[48],"Both":[49],"rulebased":[50],"model-based":[52],"methods":[53],"adapted":[55],"score":[57],"sentence":[60],"pairs.":[61,78],"The":[62],"final":[63],"filtering":[66],"system":[67],"is":[68],"reliable,":[69],"easy":[70],"build":[72],"adapt":[74],"other":[76],"language":[77]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
