{"id":"https://openalex.org/W2108387313","doi":"https://doi.org/10.1109/slt.2008.4777885","title":"Improving word segmentation for Thai speech translation","display_name":"Improving word segmentation for Thai speech translation","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2108387313","doi":"https://doi.org/10.1109/slt.2008.4777885","mag":"2108387313"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2008.4777885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2008.4777885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5445/ir/1000014800","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048512915","display_name":"Paisarn Charoenpornsawat","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paisarn Charoenpornsawat","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048512915"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.09650385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"244"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.996399998664856,"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":0.8583023548126221},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.7255880832672119},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7237434387207031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7099188566207886},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6748917698860168},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6491549611091614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6332377195358276},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6113878488540649},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5237935781478882},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5188228487968445},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5168838500976562},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5041154623031616},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47213178873062134},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4658072590827942},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4432184398174286},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11492979526519775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08440670371055603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583023548126221},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7255880832672119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7237434387207031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7099188566207886},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6748917698860168},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6491549611091614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6332377195358276},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6113878488540649},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5237935781478882},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5188228487968445},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5168838500976562},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5041154623031616},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47213178873062134},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4658072590827942},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4432184398174286},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11492979526519775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08440670371055603},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt.2008.4777885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2008.4777885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000014800","is_oa":false,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000014800","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"doc-type:conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.ira.uka.de/fileadmin/media/publication_files/SLT2008-CharoenpornsawatSchultz.pdf","raw_type":"text"},{"id":"doi:10.5445/ir/1000014800","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000014800","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5445/ir/1000014800","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000014800","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W133045130","https://openalex.org/W186939825","https://openalex.org/W229329885","https://openalex.org/W1498238796","https://openalex.org/W1583428434","https://openalex.org/W1991098482","https://openalex.org/W2074925295","https://openalex.org/W2126200140","https://openalex.org/W2136528950","https://openalex.org/W2149023888","https://openalex.org/W2548768491","https://openalex.org/W6607605056","https://openalex.org/W6630027374","https://openalex.org/W6680373036"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W4396644016","https://openalex.org/W2037894725","https://openalex.org/W2115867364","https://openalex.org/W2071465312","https://openalex.org/W2316043526","https://openalex.org/W2169467260","https://openalex.org/W2301266223","https://openalex.org/W2997067861","https://openalex.org/W2136857326"],"abstract_inverted_index":{"A":[0],"vocabulary":[1],"list":[2],"and":[3,127],"language":[4],"model":[5],"are":[6],"primary":[7],"components":[8],"in":[9],"a":[10,20,54,84],"speech":[11,124],"translation":[12,125,137],"system.":[13,148],"Generating":[14],"both":[15],"from":[16,90],"plain":[17],"text":[18,42,75],"is":[19,27,57],"straightforward":[21],"task":[22],"for":[23,30],"English.":[24],"However,":[25],"it":[26],"quite":[28],"challenging":[29],"Chinese,":[31],"Japanese,":[32],"or":[33],"Thai":[34,49],"which":[35],"provide":[36],"no":[37,44],"word":[38,45,50,118],"segmentation,":[39,51],"i.e.":[40],"the":[41,60,69,72,130,136,146],"has":[43],"boundary":[46],"delimiter.":[47],"For":[48],"maximal":[52],"matching,":[53],"lexicon-based":[55],"approach,":[56],"one":[58],"of":[59,71,101],"popular":[61],"methods.":[62],"Nevertheless":[63],"this":[64,80,91,105,113],"method":[65,81,132],"heavily":[66],"relies":[67],"on":[68,116],"coverage":[70],"lexicon.":[73],"When":[74,87],"contains":[76],"an":[77],"unknown":[78],"word,":[79],"usually":[82],"produces":[83],"wrong":[85,102],"boundary.":[86],"extracting":[88],"words":[89,95],"segmented":[92],"text,":[93],"some":[94],"will":[96],"not":[97],"be":[98],"retrieved":[99],"because":[100],"segmentation.":[103],"In":[104],"paper,":[106],"we":[107,121],"propose":[108],"statistical":[109],"techniques":[110],"to":[111,145],"tackle":[112],"problem.":[114],"Based":[115],"different":[117],"segmentation":[119],"methods":[120],"develop":[122],"various":[123],"systems":[126],"show":[128],"that":[129],"proposed":[131],"can":[133],"significantly":[134],"improve":[135],"accuracy":[138],"by":[139],"about":[140],"6.42%":[141],"BLEU":[142],"points":[143],"compared":[144],"baseline":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}