{"id":"https://openalex.org/W1524402818","doi":"https://doi.org/10.21437/interspeech.2007-542","title":"Exploiting unlabeled internal data in conditional random fields to reduce word segmentation errors for Chinese texts","display_name":"Exploiting unlabeled internal data in conditional random fields to reduce word segmentation errors for Chinese texts","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W1524402818","doi":"https://doi.org/10.21437/interspeech.2007-542","mag":"1524402818"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-542","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5030771512","display_name":"Richard Tzong\u2010Han Tsai","orcid":"https://orcid.org/0000-0003-0513-107X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Richard Tzong-Han Tsai","raw_affiliation_strings":["\u8cc7\u8a0a\u5de5\u7a0b\u5b78\u7cfb"],"affiliations":[{"raw_affiliation_string":"\u8cc7\u8a0a\u5de5\u7a0b\u5b78\u7cfb","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086549691","display_name":"Hsi-Chuan Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsi-Chuan Hung","raw_affiliation_strings":["[Academia Sinica, Institute of Information Science]"],"affiliations":[{"raw_affiliation_string":"[Academia Sinica, Institute of Information Science]","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109042526","display_name":"Hong-Jie Dai","orcid":"https://orcid.org/0000-0002-1516-7255"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Jie Dai","raw_affiliation_strings":["[Academia Sinica, Institute of Information Science]"],"affiliations":[{"raw_affiliation_string":"[Academia Sinica, Institute of Information Science]","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112054430","display_name":"Wen-Lian Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Lian Hsu","raw_affiliation_strings":["[Academia Sinica, Institute of Information Science]"],"affiliations":[{"raw_affiliation_string":"[Academia Sinica, Institute of Information Science]","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030771512"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04988535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2885","last_page":"2888"},"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":0.9997000098228455,"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":0.996399998664856,"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":0.8146597743034363},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7137534022331238},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6932898759841919},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6608893871307373},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6604959964752197},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.642910361289978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549697756767273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5385267734527588},{"id":"https://openalex.org/keywords/mainland-china","display_name":"Mainland China","score":0.4425101578235626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41162586212158203},{"id":"https://openalex.org/keywords/china","display_name":"China","score":0.13561204075813293},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08951470255851746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146597743034363},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7137534022331238},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6932898759841919},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6608893871307373},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6604959964752197},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.642910361289978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549697756767273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5385267734527588},{"id":"https://openalex.org/C107029721","wikidata":"https://www.wikidata.org/wiki/Q19188","display_name":"Mainland China","level":3,"score":0.4425101578235626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41162586212158203},{"id":"https://openalex.org/C191935318","wikidata":"https://www.wikidata.org/wiki/Q148","display_name":"China","level":2,"score":0.13561204075813293},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08951470255851746},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-542","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.105.404","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.105.404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/IASL/webpdf/paper-2007-Exploiting_Unlabeled_Internal_Data_in_Conditional_Random_Fields_to_Reduce_Word_Segmentation_Errors_for_Chinese_Texts.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W29122440","https://openalex.org/W1518670641","https://openalex.org/W1565818682","https://openalex.org/W1578379606","https://openalex.org/W2036516910","https://openalex.org/W2079656678","https://openalex.org/W2118563017","https://openalex.org/W2125838338","https://openalex.org/W2146223937","https://openalex.org/W2147880316"],"related_works":["https://openalex.org/W2393940967","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W120168696","https://openalex.org/W2153245103"],"abstract_inverted_index":{"The":[0,19],"application":[1],"of":[2,27,54,119,186,225],"text-to-speech":[3],"(TTS)":[4],"conversion":[5],"has":[6,215],"become":[7,219],"widely":[8,129],"used":[9],"in":[10,30,45,57,78,139,157],"recent":[11],"years.":[12],"Chinese":[13,36,46,232],"TTS":[14,72],"faces":[15],"several":[16],"unique":[17],"difficulties.":[18],"most":[20,128],"critical":[21],"is":[22],"caused":[23],"by":[24,149,183],"the":[25,42,51,60,90,117,127,163,191,201,216,223],"lack":[26],"word":[28,37,55,108,233],"delimiters":[29],"written":[31],"Chinese.":[32,144],"This":[33],"means":[34],"that":[35,101,169,205,212],"segmentation":[38,66,109,181,235],"(CWS)":[39],"must":[40],"be":[41],"first":[43],"step":[44],"TTS.":[47],"Unfortunately,":[48],"due":[49],"to":[50,106,190,200,218],"ambiguous":[52],"nature":[53],"boundaries":[56],"Chinese,":[58],"even":[59],"best":[61,202],"CWS":[62,131,203],"systems":[63,88,204],"make":[64],"serious":[65],"errors.":[67],"Incorrect":[68],"sentence":[69],"interpretation":[70],"causes":[71],"errors,":[73,236],"preventing":[74],"TTS\u2019s":[75],"wider":[76],"use":[77,206],"applications":[79],"such":[80],"as":[81,222],"automatic":[82],"customer":[83],"services":[84],"or":[85,153],"computer":[86],"reader":[87],"for":[89],"visually":[91],"impaired.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,122],"propose":[97],"a":[98],"novel":[99],"method":[100,214],"exploits":[102],"unlabeled":[103,175,238],"internal":[104,172,237],"data":[105,173,227,239],"reduce":[107],"errors":[110,182],"without":[111],"using":[112],"external":[113,207],"dictionaries.":[114],"To":[115],"demonstrate":[116],"generality":[118],"our":[120,124,178,195,213],"method,":[121],"verify":[123],"system":[125],"on":[126],"recognized":[130],"evaluation":[132],"tool--the":[133],"SIGHAN":[134],"bakeoff,":[135],"which":[136],"includes":[137],"datasets":[138,146],"both":[140],"traditional":[141,192],"and":[142,162,174],"simplified":[143],"These":[145],"are":[147],"provided":[148],"four":[150],"representative":[151],"academies":[152],"industrial":[154],"research":[155],"institutes":[156],"HK,":[158],"Taiwan,":[159],"Mainland":[160],"China,":[161],"U.S.":[164],"Our":[165],"experimental":[166],"results":[167],"show":[168],"with":[170],"only":[171],"test":[176,226],"data,":[177],"approach":[179,196],"reduces":[180],"an":[184],"average":[185],"15":[187],"%":[188],"compared":[189],"approach.":[193],"Moreover,":[194],"achieves":[197],"comparable":[198],"performance":[199],"resources.":[208],"Further":[209],"analysis":[210],"shows":[211],"potential":[217],"more":[220],"accurate":[221],"amount":[224],"increases.":[228],"Index":[229],"Terms:":[230],"text-to-speech,":[231],"segmentation,":[234]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}