{"id":"https://openalex.org/W3110116204","doi":"https://doi.org/10.18653/v1/2020.wmt-1.138","title":"How Should Markup Tags Be Translated?","display_name":"How Should Markup Tags Be Translated?","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3110116204","doi":"https://doi.org/10.18653/v1/2020.wmt-1.138","mag":"3110116204"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.138","pdf_url":"https://aclanthology.org/2020.wmt-1.138.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-1.138.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068124199","display_name":"Greg Hanneman","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Hanneman","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090357305","display_name":"Georgiana Dinu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgiana Dinu","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.345,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60321149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1160","last_page":"1173"},"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":0.9997000098228455,"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":0.9703999757766724,"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/markup-language","display_name":"Markup language","score":0.9636101722717285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8367059230804443},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6379625797271729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5649476647377014},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5492437481880188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4645874798297882},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3868023753166199},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37964609265327454},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.23917648196220398},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16953271627426147}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.9636101722717285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367059230804443},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6379625797271729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5649476647377014},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5492437481880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4645874798297882},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3868023753166199},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37964609265327454},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.23917648196220398},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16953271627426147},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.138","pdf_url":"https://aclanthology.org/2020.wmt-1.138.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:3110116204","is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wmt-1.138.pdf","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-1.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.138","pdf_url":"https://aclanthology.org/2020.wmt-1.138.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3110116204.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2057399676","https://openalex.org/W2148708890","https://openalex.org/W2165170939","https://openalex.org/W2606974598","https://openalex.org/W2737638662","https://openalex.org/W2759027098","https://openalex.org/W2778814079","https://openalex.org/W2951770285","https://openalex.org/W2960374072","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963648186","https://openalex.org/W2963876447","https://openalex.org/W2964121744","https://openalex.org/W2964247056","https://openalex.org/W2970069595","https://openalex.org/W2970231882","https://openalex.org/W2971134989","https://openalex.org/W2978130535","https://openalex.org/W2978206402","https://openalex.org/W2978264350","https://openalex.org/W2978449549","https://openalex.org/W2984051011","https://openalex.org/W3082674894","https://openalex.org/W3210814509"],"related_works":["https://openalex.org/W2839166850","https://openalex.org/W1523931739","https://openalex.org/W3166212183","https://openalex.org/W2306160252","https://openalex.org/W2184002268","https://openalex.org/W2930833906","https://openalex.org/W3104631073","https://openalex.org/W2340602701","https://openalex.org/W2099466889","https://openalex.org/W2759575554","https://openalex.org/W1963424616","https://openalex.org/W2791053049","https://openalex.org/W2857895251","https://openalex.org/W2500268354","https://openalex.org/W2734728700","https://openalex.org/W2826008392","https://openalex.org/W2870857044","https://openalex.org/W2267537298","https://openalex.org/W1537321305","https://openalex.org/W2927609275"],"abstract_inverted_index":{"The":[0],"ability":[1,34],"of":[2,17,27,35,50,67,84],"machine":[3],"translation":[4],"(MT)":[5],"models":[6,37],"to":[7,13,38,61],"correctly":[8],"place":[9],"markup":[10,29],"is":[11],"crucial":[12],"generating":[14],"high-quality":[15],"translations":[16],"formatted":[18],"input.":[19],"This":[20],"paper":[21],"compares":[22],"two":[23],"commonly":[24],"used":[25],"methods":[26],"representing":[28],"tags":[30],"and":[31,58,65,72],"tests":[32],"the":[33,48,63],"MT":[36],"learn":[39],"tag":[40,51,56],"placement":[41],"via":[42],"training":[43],"data":[44,53,79],"augmentation.":[45],"We":[46,70],"study":[47],"interactions":[49],"representation,":[52],"augmentation":[54],"size,":[55],"complexity,":[57],"language":[59,82],"pair":[60],"show":[62],"drawbacks":[64],"benefits":[66],"each":[68],"method.":[69],"construct":[71],"release":[73],"new":[74],"test":[75],"sets":[76],"containing":[77],"tagged":[78],"for":[80],"three":[81],"pairs":[83],"varying":[85],"difficulty.":[86]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-12-07T00:00:00"}