{"id":"https://openalex.org/W2075414095","doi":"https://doi.org/10.3115/1119250.1119260","title":"Modeling of long distance context dependency in Chinese","display_name":"Modeling of long distance context dependency in Chinese","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2075414095","doi":"https://doi.org/10.3115/1119250.1119260","mag":"2075414095"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119260","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119260","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119260","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119260","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012794465","display_name":"Guodong Zhou","orcid":"https://orcid.org/0000-0002-7887-5099"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"GuoDong Zhou","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. for Infocomm Res., Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. for Infocomm Res., Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012794465"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.1187809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"71","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9869999885559082,"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":0.9700999855995178,"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/trigram","display_name":"Trigram","score":0.9365850687026978},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7638665437698364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6852990388870239},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6194501519203186},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6145643591880798},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.6057794690132141},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6034202575683594},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5159602761268616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4214995205402374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41138288378715515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18787670135498047}],"concepts":[{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.9365850687026978},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7638665437698364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852990388870239},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6194501519203186},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6145643591880798},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.6057794690132141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6034202575683594},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5159602761268616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4214995205402374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41138288378715515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18787670135498047},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1119250.1119260","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119260","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119260","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing  -","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119260","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119260","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119260","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second SIGHAN workshop on Chinese language processing  -","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2075414095.pdf","grobid_xml":"https://content.openalex.org/works/W2075414095.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W605575788","https://openalex.org/W1589170661","https://openalex.org/W1590952807","https://openalex.org/W1844951210","https://openalex.org/W1859173823","https://openalex.org/W2029768569","https://openalex.org/W2079145130","https://openalex.org/W2098128378","https://openalex.org/W2103277165","https://openalex.org/W2121227244","https://openalex.org/W2126477387","https://openalex.org/W2134237567","https://openalex.org/W2135777451","https://openalex.org/W2165112885","https://openalex.org/W2441154163"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W2020757772","https://openalex.org/W2041167939","https://openalex.org/W2950575438","https://openalex.org/W2551914602","https://openalex.org/W1620568205","https://openalex.org/W2053242504","https://openalex.org/W79835312","https://openalex.org/W2223833155","https://openalex.org/W1600680149"],"abstract_inverted_index":{"Ngram":[0],"modeling":[1,6,71,130],"is":[2,37,126],"simple":[3],"in":[4,12,46],"language":[5,36,48],"and":[7,83],"has":[8,131],"been":[9],"widely":[10],"used":[11],"many":[13],"applications.":[14],"However,":[15],"it":[16],"can":[17,187],"only":[18],"capture":[19],"the":[20,30,40,91,101,105,111,115,120,140,152,158,161,169,173,192,197],"short":[21,92],"distance":[22,62,93,107],"context":[23,44,63,94,108],"dependency":[24,45,95,109],"within":[25,96],"an":[26,80,84,97],"N-word":[27,98,116],"window":[28,99,117],"where":[29],"largest":[31],"practical":[32],"N":[33],"for":[34],"natural":[35,47],"three.":[38],"In":[39,54,172],"meantime,":[41],"much":[42,132],"of":[43,60,77,122,144,151,160,185],"occurs":[49],"beyond":[50,114],"a":[51,68],"three-word":[52],"window.":[53],"order":[55],"to":[56],"incorporate":[57],"this":[58,65],"kind":[59],"long":[61,106],"dependency,":[64],"paper":[66],"proposes":[67],"new":[69,142],"MI-Ngram":[70,74,129],"approach.":[72],"The":[73,87],"model":[75,82,89,103,163,194],"consists":[76],"two":[78],"components:":[79],"ngram":[81,88,136],"MI":[85,102],"model.":[86,171,199],"captures":[90,104],"while":[100],"between":[110],"word":[112,155,178],"pairs":[113,156],"by":[118,164,190],"using":[119,191],"concept":[121],"mutual":[123],"information.":[124],"It":[125],"found":[127],"that":[128,149,181],"better":[133],"performance":[134],"than":[135],"modeling.":[137],"Evaluation":[138],"on":[139,176],"XINHUA":[141],"corpus":[143],"29":[145],"million":[146],"words":[147],"shows":[148,180],"inclusion":[150],"best":[153],"1,600,000":[154],"decreases":[157],"perplexity":[159],"MI-Trigram":[162,193],"20":[165],"percent":[166,184],"compared":[167,195],"with":[168,196],"trigram":[170,198],"meanwhile,":[174],"evaluation":[175],"Chinese":[177],"segmentation":[179],"about":[182],"35":[183],"errors":[186],"be":[188],"corrected":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}