{"id":"https://openalex.org/W2757041753","doi":"https://doi.org/10.18653/v1/w17-4706","title":"Target-side Word Segmentation Strategies for Neural Machine Translation","display_name":"Target-side Word Segmentation Strategies for Neural Machine Translation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2757041753","doi":"https://doi.org/10.18653/v1/w17-4706","mag":"2757041753"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4706","pdf_url":"https://www.aclweb.org/anthology/W17-4706.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 Second 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://www.aclweb.org/anthology/W17-4706.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051437051","display_name":"Matthias Huck","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Huck","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112322749","display_name":"Simon Rie\u00df","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Riess","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061754269","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-1924-0015"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"67"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9804999828338623,"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/machine-translation","display_name":"Machine translation","score":0.78984534740448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7384193539619446},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.712483286857605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6362321376800537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6202768683433533},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4701692461967468},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4502045214176178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3417440354824066},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11554089188575745},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.059842854738235474}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.78984534740448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384193539619446},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.712483286857605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6362321376800537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6202768683433533},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4701692461967468},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4502045214176178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3417440354824066},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11554089188575745},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.059842854738235474},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-4706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4706","pdf_url":"https://www.aclweb.org/anthology/W17-4706.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 Second Conference on Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4706","pdf_url":"https://www.aclweb.org/anthology/W17-4706.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 Second Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8900516709","display_name":"Health in my Language","funder_award_id":"644402","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2757041753.pdf","grobid_xml":"https://content.openalex.org/works/W2757041753.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W46679369","https://openalex.org/W1480857181","https://openalex.org/W1522301498","https://openalex.org/W1819520634","https://openalex.org/W2016856586","https://openalex.org/W2036249761","https://openalex.org/W2097341304","https://openalex.org/W2098162425","https://openalex.org/W2101105183","https://openalex.org/W2113788796","https://openalex.org/W2117997600","https://openalex.org/W2119741585","https://openalex.org/W2124807415","https://openalex.org/W2125768350","https://openalex.org/W2143134347","https://openalex.org/W2149327368","https://openalex.org/W2164529863","https://openalex.org/W2170464899","https://openalex.org/W2250332179","https://openalex.org/W2250526231","https://openalex.org/W2261339088","https://openalex.org/W2418388682","https://openalex.org/W2512924740","https://openalex.org/W2525778437","https://openalex.org/W2531207078","https://openalex.org/W2595715041","https://openalex.org/W2741026152","https://openalex.org/W2758010889","https://openalex.org/W2781601116","https://openalex.org/W2962784628","https://openalex.org/W2962801832","https://openalex.org/W2963451766","https://openalex.org/W2964053711","https://openalex.org/W2964121744","https://openalex.org/W3203149905","https://openalex.org/W4300675524"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2962780935","https://openalex.org/W4387896177","https://openalex.org/W4385557855","https://openalex.org/W2807006873","https://openalex.org/W4287236333","https://openalex.org/W2623411141","https://openalex.org/W2883671469"],"abstract_inverted_index":{"For":[0],"efficiency":[1],"considerations,":[2],"state-of-theart":[3],"neural":[4],"machine":[5],"translation":[6],"(NMT)":[7],"requires":[8],"the":[9,37],"vocabulary":[10],"to":[11,14],"be":[12],"restricted":[13],"a":[15,52],"limited-size":[16],"set":[17],"of":[18,39],"several":[19],"thousand":[20],"symbols.":[21],"This":[22],"is":[23,36],"highly":[24],"problematic":[25],"when":[26],"translating":[27],"into":[28,46],"inflected":[29],"or":[30],"compounding":[31],"languages.":[32],"A":[33],"typical":[34],"remedy":[35],"use":[38],"subword":[40],"units,":[41],"where":[42],"words":[43],"are":[44],"segmented":[45],"smaller":[47],"components.":[48],"Byte":[49],"pair":[50],"encoding,":[51],"purely":[53],"corpus-based":[54],"approach,":[55],"has":[56],"proved":[57],"effective":[58],"recently.":[59]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}
