{"id":"https://openalex.org/W1967541735","doi":"https://doi.org/10.3115/1119250.1119273","title":"A two-stage statistical word segmentation system for Chinese","display_name":"A two-stage statistical word segmentation system for Chinese","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1967541735","doi":"https://doi.org/10.3115/1119250.1119273","mag":"1967541735"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119273","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119273","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119273","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/10.3115/1119250.1119273","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101990229","display_name":"Guohong Fu","orcid":"https://orcid.org/0000-0001-6882-6181"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guohong Fu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong","[The University of Hong Kong, Hong Kong}]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"[The University of Hong Kong, Hong Kong}]","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045562512","display_name":"Kang Kwong Luke","orcid":"https://orcid.org/0000-0002-2883-3659"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"K. K. Luke","raw_affiliation_strings":["The University of Hong Kong, Hong Kong","[The University of Hong Kong, Hong Kong}]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"[The University of Hong Kong, Hong Kong}]","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7507,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9317143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"156","last_page":"159"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9969000220298767,"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":0.9962000250816345,"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/bigram","display_name":"Bigram","score":0.9433938264846802},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7766757011413574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228822708129883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6769036054611206},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6562705039978027},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6379833221435547},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5717812776565552},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5175884962081909},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4655708968639374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45096638798713684},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.4456678330898285},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.43706899881362915},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16368070244789124},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13539165258407593},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1198820173740387}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9433938264846802},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7766757011413574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228822708129883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769036054611206},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6562705039978027},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6379833221435547},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5717812776565552},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5175884962081909},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4655708968639374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45096638798713684},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.4456678330898285},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.43706899881362915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16368070244789124},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13539165258407593},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1198820173740387},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1119250.1119273","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119273","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119273","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.476","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/sighan/pdf/Fu.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.5783","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.5783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/sighan/pdfs/Fu.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119273","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119273","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119273","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":[{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1967541735.pdf","grobid_xml":"https://content.openalex.org/works/W1967541735.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1597533204","https://openalex.org/W1991133427","https://openalex.org/W2001831858"],"related_works":["https://openalex.org/W2134942375","https://openalex.org/W2067499868","https://openalex.org/W2041541227","https://openalex.org/W167435909","https://openalex.org/W2122028591","https://openalex.org/W2124470186","https://openalex.org/W2126405470","https://openalex.org/W1981146289","https://openalex.org/W4388551919","https://openalex.org/W38605570"],"abstract_inverted_index":{"In":[0],"this":[1,43],"paper":[2],"we":[3],"present":[4],"a":[5],"two-stage":[6],"statistical":[7],"word":[8,15],"segmentation":[9],"system":[10,21],"for":[11],"Chinese":[12,32],"based":[13],"on":[14,24,42],"bigram":[16],"and":[17,40],"word-formation":[18],"models.":[19],"This":[20],"was":[22],"evaluated":[23],"Peking":[25],"University":[26],"corpora":[27],"at":[28],"the":[29],"First":[30],"International":[31],"Word":[33],"Segmentation":[34],"Bakeoff.":[35],"We":[36],"also":[37],"give":[38],"results":[39],"discussions":[41],"evaluation.":[44]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}