{"id":"https://openalex.org/W2251881903","doi":"https://doi.org/10.3115/v1/w14-5513","title":"Character-Cluster-Based Segmentation using Monolingual and Bilingual Information for Statistical Machine Translation","display_name":"Character-Cluster-Based Segmentation using Monolingual and Bilingual Information for Statistical Machine Translation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251881903","doi":"https://doi.org/10.3115/v1/w14-5513","mag":"2251881903"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5513","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5513","pdf_url":"https://aclanthology.org/W14-5513.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 Workshop on South and Southeast Asian Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-5513.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029755172","display_name":"Vipas Sutantayawalee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vipas Sutantayawalee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022597257","display_name":"Peerachet Porkeaw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peerachet Porkeaw","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063918994","display_name":"Thepchai Supnithi","orcid":"https://orcid.org/0000-0003-0173-1908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thepchai Supnithi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053857897","display_name":"Prachya Boonkwan","orcid":"https://orcid.org/0000-0003-1405-1071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prachya Boonkwan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083058484","display_name":"Sitthaa Phaholphinyo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sitthaa Phaholphinyo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029755172"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14338787,"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":"94","last_page":"101"},"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":0.9993000030517578,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8447216749191284},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7688174247741699},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.748769998550415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7222915887832642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7136998176574707},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6791531443595886},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6572059392929077},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5984215140342712},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5617424249649048},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5048828721046448},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4356161653995514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42977339029312134},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.417946457862854},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4113613963127136},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41098159551620483},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15796241164207458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08268597722053528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447216749191284},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7688174247741699},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.748769998550415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7222915887832642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7136998176574707},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6791531443595886},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6572059392929077},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5984215140342712},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5617424249649048},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5048828721046448},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4356161653995514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42977339029312134},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.417946457862854},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4113613963127136},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41098159551620483},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15796241164207458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08268597722053528},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-5513","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5513","pdf_url":"https://aclanthology.org/W14-5513.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 Workshop on South and Southeast Asian Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.8288","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.8288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-5513.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5513","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5513","pdf_url":"https://aclanthology.org/W14-5513.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 Workshop on South and Southeast Asian Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.41999998688697815,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251881903.pdf","grobid_xml":"https://content.openalex.org/works/W2251881903.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W162854924","https://openalex.org/W2067347800","https://openalex.org/W2131988669","https://openalex.org/W2138753018","https://openalex.org/W2144783305","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2787109023"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W3011059803","https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2386957102"],"abstract_inverted_index":{"We":[0,136],"present":[1],"a":[2,51],"novel":[3],"segmentation":[4],"approach":[5],"for":[6,216],"Phrase-Based":[7],"Statistical":[8],"Machine":[9],"Translation":[10],"(PB-SMT)":[11],"to":[12,36,43,184,199,213],"languages":[13],"where":[14],"word":[15,87],"boundaries":[16,212],"are":[17,73,124,163],"not":[18,196],"obviously":[19],"marked":[20],"by":[21,104,118],"using":[22,146],"both":[23],"monolingual":[24,78,102],"and":[25,28,109,130,150,180],"bilingual":[26,71,121],"information":[27,72,122],"demonstrate":[29],"that":[30,134],"(1)":[31],"unsegmented":[32,101,185],"corpus":[33,46,103,179,186],"is":[34,57],"able":[35],"provide":[37],"the":[38,62,100,115,120,138,152,178,209],"nearly":[39],"identical":[40],"result":[41,117],"compares":[42],"manually":[44,189],"segmented":[45,79,116,190],"in":[47,159],"PB-SMT":[48,65,144],"task":[49,66,145],"when":[50,70],"good":[52],"heuristic":[53],"character":[54,92,98,106,125,210],"clustering":[55],"algorithm":[56],"applied":[58,183],"on":[59,75,86,91,143,176],"it,":[60],"(2)":[61],"performance":[63],"of":[64,77,84,140,155,167,206],"has":[67],"significantly":[68],"increased":[69],"used":[74],"top":[76],"result.":[80,135],"Our":[81],"technique,":[82],"instead":[83],"focusing":[85],"separation,":[88],"mainly":[89],"concentrate":[90],"clustering.":[93],"First,":[94,170],"we":[95,113],"cluster":[96,126,211],"each":[97],"from":[99],"employing":[105],"co-occurrence":[107,128],"statistics":[108],"orthographic":[110],"insight.":[111],"Secondly,":[112],"enhance":[114],"incorporating":[119],"which":[123],"alignment,":[127],"frequency":[129],"alignment":[131],"confidence":[132],"into":[133],"evaluate":[137],"effectiveness":[139],"our":[141,168,171],"method":[142,172],"English-Thai":[147],"language":[148,201,218],"pair":[149,202],"report":[151],"best":[153],"improvement":[154],"8.1":[156],"%":[157],"increase":[158],"BLEU":[160],"score.":[161],"There":[162],"two":[164],"main":[165],"advantages":[166],"approach.":[169],"requires":[173],"less":[174],"effort":[175],"developing":[177],"can":[181],"be":[182,214],"or":[187],"poor-quality":[188],"corpus.":[191],"Second,":[192],"this":[193],"technique":[194],"does":[195],"only":[197],"limited":[198],"specific":[200],"but":[203],"also":[204],"capable":[205],"automatically":[207],"adjust":[208],"suitable":[215],"other":[217],"pairs.":[219],"1":[220]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}