{"id":"https://openalex.org/W2046199218","doi":"https://doi.org/10.3115/1119250.1119270","title":"Combining segmenter and chunker for Chinese word segmentation","display_name":"Combining segmenter and chunker for Chinese word segmentation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2046199218","doi":"https://doi.org/10.3115/1119250.1119270","mag":"2046199218"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119270","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119270","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1119270&type=pdf","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1119270&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002196974","display_name":"Masayuki Asahara","orcid":"https://orcid.org/0000-0002-5178-7275"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Asahara","raw_affiliation_strings":["Graduate School of Information Science Nara Institute of Science and Technology, Japan","Nara Institute of Science and Technology , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Nara Institute of Science and Technology , Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084419306","display_name":"Chooi Ling Goh","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chooi Ling Goh","raw_affiliation_strings":["Nara Institute of Science and Technology , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology , Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Nara Institute of Science and Technology , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology , Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072032804","display_name":"Y\u016bji Matsumoto","orcid":"https://orcid.org/0000-0003-4946-9574"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuji Matsumoto","raw_affiliation_strings":["Nara Institute of Science and Technology , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology , Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"144","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9941999912261963,"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":0.9805999994277954,"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/word","display_name":"Word (group theory)","score":0.8255395889282227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7705681324005127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7471791505813599},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6746741533279419},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6277657747268677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6001189947128296},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5809014439582825},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4876593351364136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38796770572662354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3878037631511688},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17187422513961792}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8255395889282227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705681324005127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7471791505813599},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6746741533279419},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6277657747268677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6001189947128296},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5809014439582825},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4876593351364136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38796770572662354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3878037631511688},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17187422513961792},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1119250.1119270","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119270","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1119270&type=pdf","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:10.3115/1119250.1119270","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119270","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1119270&type=pdf","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/F4320315716","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2046199218.pdf","grobid_xml":"https://content.openalex.org/works/W2046199218.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W793766733","https://openalex.org/W1988995507","https://openalex.org/W2148603752","https://openalex.org/W2156909104"],"related_works":["https://openalex.org/W1974738623","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":{"Our":[0],"proposed":[1],"method":[2],"is":[3,61],"to":[4,98],"use":[5],"a":[6,13],"Hidden":[7,29],"Markov":[8,30],"Model-based":[9,31],"word":[10,20,32,35,39,66,101],"segmenter":[11,36],"and":[12,46,58,68],"Support":[14,86],"Vector":[15,87],"Machine-based":[16,88],"chunker":[17,89],"for":[18,81],"Chinese":[19],"segmentation.":[21],"Firstly,":[22],"input":[23],"sentences":[24],"are":[25,53,75],"analyzed":[26],"by":[27],"the":[28,50,64,69,72,79,82,85,100],"segmenter.":[33],"The":[34],"produces":[37],"n-best":[38],"candidates":[40],"together":[41,93],"with":[42,63],"some":[43],"class":[44,67],"information":[45],"confidence":[47],"measures.":[48],"Secondly,":[49],"extracted":[51],"words":[52,95],"broken":[54],"into":[55,94],"character":[56,60,91],"units":[57,92],"each":[59],"annotated":[62],"possible":[65],"position":[70],"in":[71],"word,":[73],"which":[74],"then":[76],"used":[77],"as":[78,97],"features":[80],"chunker.":[83],"Finally,":[84],"brings":[90],"so":[96],"determine":[99],"boundaries.":[102]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}