{"id":"https://openalex.org/W2964030816","doi":"https://doi.org/10.18653/v1/p18-3016","title":"Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models","display_name":"Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2964030816","doi":"https://doi.org/10.18653/v1/p18-3016","mag":"2964030816"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-3016","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-3016","pdf_url":"https://www.aclweb.org/anthology/P18-3016.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 ACL 2018, Student Research Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-3016.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010294982","display_name":"Satoru Katsumata","orcid":"https://orcid.org/0000-0002-9028-3598"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Katsumata","raw_affiliation_strings":["Tokyo Metropolitan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113842535","display_name":"Yukio Matsumura","orcid":null},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukio Matsumura","raw_affiliation_strings":["Tokyo Metropolitan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069962105","display_name":"Hayahide Yamagishi","orcid":null},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayahide Yamagishi","raw_affiliation_strings":["Tokyo Metropolitan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061931124","display_name":"Mamoru Komachi","orcid":"https://orcid.org/0000-0003-1166-1739"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mamoru Komachi","raw_affiliation_strings":["Tokyo Metropolitan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.169,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64658682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"112","last_page":"119"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9962999820709229,"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":0.8059982657432556},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7762895822525024},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7390514016151428},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6489379405975342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5989136695861816},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.579998254776001},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5428372621536255},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.514351487159729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5100443959236145},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5037240386009216},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48276105523109436},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15967008471488953},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07132256031036377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8059982657432556},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7762895822525024},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7390514016151428},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6489379405975342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989136695861816},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.579998254776001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5428372621536255},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.514351487159729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5100443959236145},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5037240386009216},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48276105523109436},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15967008471488953},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07132256031036377},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-3016","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-3016","pdf_url":"https://www.aclweb.org/anthology/P18-3016.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 ACL 2018, Student Research Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-3016","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-3016","pdf_url":"https://www.aclweb.org/anthology/P18-3016.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 ACL 2018, Student Research Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964030816.pdf","grobid_xml":"https://content.openalex.org/works/W2964030816.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1525595230","https://openalex.org/W1902237438","https://openalex.org/W2064418625","https://openalex.org/W2066636486","https://openalex.org/W2098297786","https://openalex.org/W2101105183","https://openalex.org/W2124725212","https://openalex.org/W2130337399","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2138621811","https://openalex.org/W2144950812","https://openalex.org/W2148708890","https://openalex.org/W2157331557","https://openalex.org/W2170527467","https://openalex.org/W2252235727","https://openalex.org/W2252272516","https://openalex.org/W2321916036","https://openalex.org/W2470324779","https://openalex.org/W2525778437","https://openalex.org/W2576482813","https://openalex.org/W2949335953","https://openalex.org/W2962784628","https://openalex.org/W2962901607","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Encoder-decoder":[0],"models":[1],"typically":[2],"only":[3,53],"employ":[4],"words":[5,29,46],"that":[6,30,89,95,115],"are":[7],"frequently":[8],"used":[9],"in":[10,34],"the":[11,16,63,102],"training":[12],"corpus":[13],"to":[14,71],"reduce":[15],"computational":[17],"costs":[18],"and":[19,76],"exclude":[20],"noise.":[21],"However,":[22],"this":[23,83],"vocabulary":[24],"set":[25],"may":[26],"still":[27],"include":[28],"interfere":[31],"with":[32,110],"learning":[33,48],"encoder-decoder":[35],"models.":[36],"This":[37],"paper":[38],"proposes":[39],"a":[40,86,97],"method":[41,70,84,104],"for":[42,47,105],"selecting":[43],"more":[44,93],"suitable":[45],"encoders":[49],"by":[50],"utilizing":[51],"not":[52],"frequency":[54],"but":[55],"also":[56],"cooccurrence":[57],"information,":[58],"which":[59],"we":[60],"capture":[61],"using":[62],"HITS":[64],"algorithm.":[65],"We":[66],"apply":[67],"our":[68],"proposed":[69],"two":[72],"tasks:":[73],"machine":[74],"translation":[75],"grammatical":[77,107],"error":[78,108],"correction.":[79],"For":[80],"Japanese-to-English":[81],"translation,":[82],"achieves":[85],"BLEU":[87],"score":[88],"is":[90,116],"0.56":[91],"points":[92,118],"than":[94],"of":[96],"baseline.":[98],"Furthermore,":[99],"it":[100],"outperforms":[101],"baseline":[103],"English":[106],"correction,":[109],"an":[111],"F":[112],"0.5":[113],"-measure":[114],"1.48":[117],"higher.":[119]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}