{"id":"https://openalex.org/W2108220507","doi":"https://doi.org/10.3115/1075096.1075131","title":"Improved source-channel models for Chinese word segmentation","display_name":"Improved source-channel models for Chinese word segmentation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2108220507","doi":"https://doi.org/10.3115/1075096.1075131","mag":"2108220507"},"language":"en","primary_location":{"id":"doi:10.3115/1075096.1075131","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075131","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075131","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075131","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399461","display_name":"Mu Li","orcid":"https://orcid.org/0000-0002-4433-2301"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Li","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066941389","display_name":"Changning Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang-Ning Huang","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"272","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.994700014591217,"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":0.8435754776000977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7330073118209839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.680208683013916},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6364702582359314},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.632757842540741},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6318077445030212},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6058087944984436},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.524293839931488},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5051568150520325},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47715944051742554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42482322454452515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18427643179893494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435754776000977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7330073118209839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.680208683013916},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6364702582359314},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.632757842540741},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6318077445030212},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6058087944984436},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.524293839931488},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5051568150520325},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47715944051742554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42482322454452515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18427643179893494},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1075096.1075131","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075131","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075131","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1075096.1075131","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075131","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075131","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2108220507.pdf","grobid_xml":"https://content.openalex.org/works/W2108220507.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W41384227","https://openalex.org/W1558333962","https://openalex.org/W1564640168","https://openalex.org/W1973200086","https://openalex.org/W1974967573","https://openalex.org/W1979262500","https://openalex.org/W1979557360","https://openalex.org/W1996034123","https://openalex.org/W2083979457","https://openalex.org/W2129287413","https://openalex.org/W2134237567","https://openalex.org/W2420187884","https://openalex.org/W3010180081","https://openalex.org/W4255764218","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2785359773","https://openalex.org/W2159591557","https://openalex.org/W2058548953"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,40,75],"Chinese":[4,14,17,50,97],"word":[5,54],"segmentation":[6],"system":[7,38,71,102],"that":[8,93],"uses":[9],"improved":[10],"source-channel":[11],"models":[12],"of":[13,23,48,69,96],"sentence":[15],"generation.":[16],"words":[18,98],"are":[19],"defined":[20],"as":[21],"one":[22],"the":[24,44,70,91,94],"following":[25],"four":[26,45],"types:":[27],"lexicon":[28],"words,":[29,32],"morphologically":[30],"derived":[31],"factoids,":[33],"and":[34,62,80],"named":[35,64],"entities.":[36],"Our":[37],"provides":[39],"unified":[41],"approach":[42],"to":[43,103],"fundamental":[46],"features":[47],"word-level":[49],"language":[51],"processing:":[52],"(1)":[53],"segmentation,":[55],"(2)":[56],"morphological":[57],"analysis,":[58],"(3)":[59],"factoid":[60],"detection,":[61],"(4)":[63],"entity":[65],"recognition.":[66],"The":[67],"performance":[68],"is":[72,81],"evaluated":[73],"on":[74],"manually":[76],"annotated":[77],"test":[78],"set,":[79],"also":[82],"compared":[83],"with":[84],"several":[85],"state-of-the-art":[86],"systems,":[87],"taking":[88],"into":[89],"account":[90],"fact":[92],"definition":[95],"often":[99],"varies":[100],"from":[101],"system.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}