{"id":"https://openalex.org/W2016338022","doi":"https://doi.org/10.1145/1667780.1667788","title":"Language independent word segmentation for statistical machine translation","display_name":"Language independent word segmentation for statistical machine translation","publication_year":2009,"publication_date":"2009-12-03","ids":{"openalex":"https://openalex.org/W2016338022","doi":"https://doi.org/10.1145/1667780.1667788","mag":"2016338022"},"language":"en","primary_location":{"id":"doi:10.1145/1667780.1667788","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1667780.1667788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Universal Communication Symposium","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039892950","display_name":"Michael Paul","orcid":"https://orcid.org/0000-0001-8479-110X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Michael Paul","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan","National Institute of Information and Communications Technology (NiCT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NiCT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081198426","display_name":"Andrew Finch","orcid":"https://orcid.org/0000-0002-7067-7098"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andrew Finch","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan","National Institute of Information and Communications Technology (NiCT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NiCT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033318800","display_name":"Eiichiro Sumita","orcid":"https://orcid.org/0000-0002-1028-4399"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiichiro Sumita","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan","National Institute of Information and Communications Technology (NiCT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NiCT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039892950"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.4362,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71497244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"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":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9937999844551086,"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":0.8816554546356201},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8572522401809692},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7491964101791382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7223248481750488},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6957746744155884},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6368858814239502},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5446627736091614},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5293845534324646},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5083021521568298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49111148715019226},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.4862631559371948},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.4587147533893585},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4482540786266327},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4238876700401306},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.37016379833221436},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08645915985107422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8816554546356201},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8572522401809692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7491964101791382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7223248481750488},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6957746744155884},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6368858814239502},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5446627736091614},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5293845534324646},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5083021521568298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49111148715019226},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.4862631559371948},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.4587147533893585},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4482540786266327},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4238876700401306},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.37016379833221436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08645915985107422},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1667780.1667788","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1667780.1667788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Universal Communication Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G570406598","display_name":null,"funder_award_id":"19500137","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1773803948","https://openalex.org/W1973200086","https://openalex.org/W2074546930","https://openalex.org/W2095907708","https://openalex.org/W2096175520","https://openalex.org/W2096184104","https://openalex.org/W2101105183","https://openalex.org/W2122228338","https://openalex.org/W2123301721","https://openalex.org/W2127134333","https://openalex.org/W2131988669","https://openalex.org/W2156985047","https://openalex.org/W2160842254","https://openalex.org/W2161952424","https://openalex.org/W2769235496","https://openalex.org/W2776926572","https://openalex.org/W2854388562","https://openalex.org/W2857753300","https://openalex.org/W2952343510","https://openalex.org/W3021371423","https://openalex.org/W6637852806"],"related_works":["https://openalex.org/W1559710535","https://openalex.org/W2027317339","https://openalex.org/W4312364893","https://openalex.org/W4283020986","https://openalex.org/W2997015083","https://openalex.org/W4318811770","https://openalex.org/W2550455130","https://openalex.org/W2596454883","https://openalex.org/W4288754596","https://openalex.org/W3013436002"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,90],"unsupervised":[4],"word":[5,10,46,82],"segmentation":[6,83],"algorithm":[7,76],"that":[8,84,107,115],"identifies":[9],"boundaries":[11],"in":[12,15,51],"continuous":[13],"text":[14],"order":[16],"to":[17,38,43,58,65,79],"optimize":[18],"the":[19,44,52,59,81,86,95,108],"translation":[20,25,87],"quality":[21,88],"of":[22,89],"statistical":[23],"machine":[24],"(SMT)":[26],"approaches.":[27],"The":[28],"proposed":[29,109],"method":[30,110],"is":[31,77],"language-independent":[32],"and":[33,71],"uses":[34],"a":[35,66,72,112],"parallel":[36],"corpus":[37],"align":[39],"source":[40,68,119],"language":[41,69,120],"characters":[42,56],"corresponding":[45],"units":[47],"separated":[48],"by":[49],"whitespace":[50],"target":[53,61],"language.":[54],"Successive":[55],"aligned":[57],"same":[60],"words":[62],"are":[63],"merged":[64],"larger":[67],"unit":[70],"Maximum":[73],"Entropy":[74],"(ME)":[75],"applied":[78],"learn":[80],"optimizes":[85],"SMT":[91],"system":[92,114],"trained":[93],"on":[94],"re-segmented":[96],"bitext.":[97],"Experimental":[98],"results":[99],"translating":[100],"five":[101],"Asian":[102],"languages":[103],"into":[104],"English":[105],"revealed":[106],"outperforms":[111],"baseline":[113],"translates":[116],"unigram":[117],"segmented":[118],"sentences.":[121]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}