{"id":"https://openalex.org/W2072278013","doi":"https://doi.org/10.3115/1119250.1119272","title":"Chinese word segmentation at Peking University","display_name":"Chinese word segmentation at Peking University","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2072278013","doi":"https://doi.org/10.3115/1119250.1119272","mag":"2072278013"},"language":"en","primary_location":{"id":"doi:10.3115/1119250.1119272","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119272","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119272","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":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119272","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034057704","display_name":"Huiming Duan","orcid":"https://orcid.org/0000-0003-3458-3905"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duan Huiming","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101160146","display_name":"Xiaojing Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bai Xiaojing","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021459300","display_name":"Baobao Chang","orcid":"https://orcid.org/0000-0003-2824-6750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Baobao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052324373","display_name":"Shiwen Yu","orcid":"https://orcid.org/0000-0002-8514-3195"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Shiwen","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"152","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9702000021934509,"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":0.9702000021934509,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9308000206947327,"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":0.7933363914489746},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.7767965793609619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7717037200927734},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7337256073951721},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7303334474563599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6351596713066101},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5816382169723511},{"id":"https://openalex.org/keywords/word-processing","display_name":"Word processing","score":0.4990730285644531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42003774642944336},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24352261424064636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1254120171070099}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7933363914489746},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7767965793609619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717037200927734},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7337256073951721},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7303334474563599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6351596713066101},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5816382169723511},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.4990730285644531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42003774642944336},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24352261424064636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1254120171070099},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1119250.1119272","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119272","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119272","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:10.1.1.476.8132","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.476.8132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wing.comp.nus.edu.sg/~antho/W/W03/W03-1722.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.5072","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.5072","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/Huiming.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.7174","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.7174","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/ps/Huiming.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1119250.1119272","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119250.1119272","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119250.1119272","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2072278013.pdf","grobid_xml":"https://content.openalex.org/works/W2072278013.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1498441903"],"related_works":["https://openalex.org/W254547640","https://openalex.org/W1970933446","https://openalex.org/W1964658544","https://openalex.org/W2737370579","https://openalex.org/W2111662565","https://openalex.org/W1038246009","https://openalex.org/W2978383222","https://openalex.org/W3034416867","https://openalex.org/W2530017491","https://openalex.org/W2172629291"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,68],"is":[2,50],"the":[3,11,14,24,83],"first":[4],"step":[5],"in":[6,45,82],"Chinese":[7],"information":[8],"processing,":[9],"and":[10,20,63],"performance":[12],"of":[13,57,67],"segmenter,":[15],"therefore,":[16],"has":[17],"a":[18,78],"direct":[19],"great":[21],"influence":[22],"on":[23],"processing":[25],"steps":[26],"that":[27,48,64],"follow.":[28],"Different":[29],"segmenters":[30],"will":[31,43],"give":[32],"different":[33,65],"results":[34,66],"when":[35],"handling":[36],"issues":[37],"like":[38],"word":[39,58],"boundary.":[40],"And":[41],"we":[42],"present":[44],"this":[46],"paper":[47],"there":[49],"no":[51],"need":[52],"for":[53,60],"an":[54],"absolute":[55],"definition":[56],"boundary":[59],"all":[61],"segmenters,":[62],"shall":[69],"be":[70],"acceptable":[71],"if":[72],"they":[73],"can":[74],"help":[75],"to":[76],"reach":[77],"correct":[79],"syntactic":[80],"analysis":[81],"end.":[84]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}