{"id":"https://openalex.org/W2060804398","doi":"https://doi.org/10.3115/1119250.1119274","title":"Integrating ngram model and case-based learning for Chinese word segmentation","display_name":"Integrating ngram model and case-based learning for Chinese word segmentation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2060804398","doi":"https://doi.org/10.3115/1119250.1119274","mag":"2060804398"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119274","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119274","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/10.3115/1119250.1119274","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069506463","display_name":"Chunyu Kit","orcid":"https://orcid.org/0000-0002-6445-7400"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chunyu Kit","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong","City University of Hong Kong , Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong , Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026967592","display_name":"Zhiming Xu","orcid":"https://orcid.org/0000-0003-1654-7361"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiming Xu","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong","City University of Hong Kong , Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong , Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031246043","display_name":"Jonathan J. Webster","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jonathan J. Webster","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong","City University of Hong Kong , Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong , Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4065,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8507236,"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":"160","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9891999959945679,"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":0.806760311126709},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.7445647120475769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6839872002601624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6624559760093689},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6412516832351685},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6195043325424194},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5622962117195129},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4519878327846527},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4459201693534851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3893011808395386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19825497269630432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806760311126709},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7445647120475769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6839872002601624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6624559760093689},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6412516832351685},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6195043325424194},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5622962117195129},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4519878327846527},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4459201693534851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3893011808395386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19825497269630432},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1119250.1119274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119274","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119274","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:10.3115/1119250.1119274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119274","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119274","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2060804398.pdf","grobid_xml":"https://content.openalex.org/works/W2060804398.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W183965307","https://openalex.org/W1554031433","https://openalex.org/W1984676939","https://openalex.org/W1991133427","https://openalex.org/W2049633694","https://openalex.org/W2217873082","https://openalex.org/W2789158071"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W2944691285","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334"],"abstract_inverted_index":{"This":[0,35],"paper":[1],"presents":[2],"our":[3,52],"recent":[4],"work":[5],"for":[6,25,54,69],"participation":[7],"in":[8,38],"the":[9,63],"First":[10],"International":[11],"Chinese":[12],"Word":[13],"Segmentation":[14],"Bake-off":[15],"(ICWSB-1).":[16],"It":[17],"is":[18],"based":[19],"on":[20],"a":[21,29,44],"general-purpose":[22],"ngram":[23],"model":[24,56],"word":[26,75],"segmentation":[27],"and":[28,58,66],"case-based":[30],"learning":[31],"approach":[32],"to":[33],"disambiguation.":[34],"system":[36],"excels":[37],"identifying":[39],"in-vocabulary":[40],"(IV)":[41],"words,":[42],"achieving":[43],"recall":[45],"of":[46],"around":[47],"96-98%.":[48],"Here":[49],"we":[50],"present":[51],"strategies":[53],"language":[55],"training":[57],"disambiguation":[59],"rule":[60],"learning,":[61],"analyze":[62],"system's":[64],"performance,":[65],"discuss":[67],"areas":[68],"further":[70],"improvement,":[71],"e.g.,":[72],"out-of-vocabulary":[73],"(OOV)":[74],"discovery.":[76]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}