{"id":"https://openalex.org/W2535151237","doi":"https://doi.org/10.18653/v1/w17-4102","title":"Learning variable length units for SMT between related languages via Byte Pair Encoding","display_name":"Learning variable length units for SMT between related languages via Byte Pair Encoding","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2535151237","doi":"https://doi.org/10.18653/v1/w17-4102","mag":"2535151237"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4102","pdf_url":"https://www.aclweb.org/anthology/W17-4102.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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4102.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052909911","display_name":"Anoop Kunchukuttan","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anoop Kunchukuttan","raw_affiliation_strings":["Center For Indian Language Technology Department of Computer Science & Engineering Indian Institute of Technology Bombay","Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center For Indian Language Technology Department of Computer Science & Engineering Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100828","display_name":"Pushpak Bhattacharyya","orcid":"https://orcid.org/0000-0001-5319-5508"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pushpak Bhattacharyya","raw_affiliation_strings":["Center For Indian Language Technology Department of Computer Science & Engineering Indian Institute of Technology Bombay","Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center For Indian Language Technology Department of Computer Science & Engineering Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.4164,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60522521,"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":"14","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9937000274658203,"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":0.9807000160217285,"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":0.7656257152557373},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.756837010383606},{"id":"https://openalex.org/keywords/writing-system","display_name":"Writing system","score":0.6762146949768066},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.641659677028656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5437394976615906},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5329614281654358},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5185621380805969},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.518365204334259},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5048778653144836},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5046271085739136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4962776303291321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44469594955444336},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3660876750946045},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.34143346548080444},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16670995950698853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15651097893714905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656257152557373},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.756837010383606},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.6762146949768066},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.641659677028656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5437394976615906},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5329614281654358},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5185621380805969},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.518365204334259},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5048778653144836},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5046271085739136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4962776303291321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44469594955444336},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3660876750946045},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.34143346548080444},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16670995950698853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15651097893714905},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w17-4102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4102","pdf_url":"https://www.aclweb.org/anthology/W17-4102.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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1610.06510","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.06510","pdf_url":"https://arxiv.org/pdf/1610.06510","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2535151237","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1610.06510.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1610.06510","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1610.06510","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4102","pdf_url":"https://www.aclweb.org/anthology/W17-4102.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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2535151237.pdf","grobid_xml":"https://content.openalex.org/works/W2535151237.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963729818","https://openalex.org/W2951948758","https://openalex.org/W3094381773","https://openalex.org/W2803399609","https://openalex.org/W2888195294","https://openalex.org/W2964002616","https://openalex.org/W1903810641","https://openalex.org/W3011874709","https://openalex.org/W2401952247","https://openalex.org/W2963676641","https://openalex.org/W1496925889","https://openalex.org/W2972903407","https://openalex.org/W2009840120","https://openalex.org/W1483055307","https://openalex.org/W2948845926","https://openalex.org/W2069712814","https://openalex.org/W2095255562","https://openalex.org/W2912492482","https://openalex.org/W2032322585","https://openalex.org/W2130106985"],"abstract_inverted_index":{"We":[0,61],"explore":[1],"the":[2,35,46],"use":[3,94],"of":[4,72],"segments":[5],"learnt":[6],"using":[7],"Byte":[8],"Pair":[9],"Encoding":[10],"(referred":[11],"to":[12,76],"as":[13,16,51,70],"BPE":[14,44,64,97,106],"units)":[15],"basic":[17,38,52],"units":[18,39,65,71,109],"for":[19,40,89,110],"statistical":[20],"machine":[21],"translation":[22,42],"between":[23],"related":[24],"languages":[25,90],"and":[26,102,126],"compare":[27],"it":[28],"with":[29],"orthographic":[30,55,68,83],"syllables,":[31],"which":[32],"are":[33,57,117],"currently":[34],"best":[36],"performing":[37],"this":[41],"task.":[43],"identifies":[45],"most":[47],"frequent":[48],"character":[49],"sequences":[50],"units,":[53],"while":[54],"syllables":[56,69,84],"linguistically":[58],"motivated":[59],"pseudo-syllables.":[60],"show":[62,104],"that":[63,105],"modestly":[66],"outperform":[67],"translation,":[73],"showing":[74],"up":[75],"11%":[77],"increase":[78],"in":[79],"BLEU":[80],"score.":[81],"While":[82],"can":[85],"be":[86],"used":[87],"only":[88],"whose":[91],"writing":[92,99,112,127],"systems":[93,113],"vowel":[95],"representations,":[96],"is":[98],"system":[100],"independent":[101],"we":[103],"outperforms":[107],"other":[108],"nonvowel":[111],"too.":[114],"Our":[115],"results":[116],"supported":[118],"by":[119],"extensive":[120],"experimentation":[121],"spanning":[122],"multiple":[123],"language":[124],"families":[125],"systems.":[128]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}