{"id":"https://openalex.org/W2134873765","doi":"https://doi.org/10.3115/1220175.1220244","title":"A comparison and semi-quantitative analysis of words and character-bigrams as features in Chinese text categorization","display_name":"A comparison and semi-quantitative analysis of words and character-bigrams as features in Chinese text categorization","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2134873765","doi":"https://doi.org/10.3115/1220175.1220244","mag":"2134873765"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220244","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220244","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220244","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","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/10.3115/1220175.1220244","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036610839","display_name":"Jingyang Li","orcid":"https://orcid.org/0000-0002-1857-3814"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101732547","display_name":"Zhang Xian","orcid":"https://orcid.org/0000-0002-6448-8004"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.996399998664856,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9696584939956665},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7920366525650024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302581071853638},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7261072397232056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6786477565765381},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6763562560081482},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6378127932548523},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5589578747749329},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4761331379413605},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45029139518737793},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.2697283625602722},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21284699440002441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10829606652259827}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9696584939956665},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7920366525650024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302581071853638},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7261072397232056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6786477565765381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6763562560081482},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6378127932548523},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5589578747749329},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4761331379413605},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45029139518737793},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.2697283625602722},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21284699440002441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10829606652259827},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1220175.1220244","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220244","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220244","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.4579","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.4579","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/P/P06/P06-1069.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220244","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220244","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220244","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2134873765.pdf","grobid_xml":"https://content.openalex.org/works/W2134873765.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W114039280","https://openalex.org/W1491771064","https://openalex.org/W1547649215","https://openalex.org/W1564518192","https://openalex.org/W1660390307","https://openalex.org/W1850664189","https://openalex.org/W1978394996","https://openalex.org/W2040241219","https://openalex.org/W2060234482","https://openalex.org/W2096152098","https://openalex.org/W2118020653","https://openalex.org/W2147152072","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2163051611","https://openalex.org/W2198380824","https://openalex.org/W2321452791","https://openalex.org/W2435251607","https://openalex.org/W3142894668","https://openalex.org/W4245025199"],"related_works":["https://openalex.org/W2197825247","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2078570174","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2035261173","https://openalex.org/W2106892947"],"abstract_inverted_index":{"Words":[0],"and":[1,57,68,87],"character-bigrams":[2,82],"are":[3,83],"both":[4],"used":[5],"as":[6,22,53],"features":[7,23],"in":[8,90],"Chinese":[9,25],"text":[10,26,91],"processing":[11],"tasks,":[12],"but":[13],"no":[14],"systematic":[15],"comparison":[16,39],"or":[17],"analysis":[18,60],"of":[19,65],"their":[20,66],"values":[21],"for":[24,75],"categorization":[27,92],"has":[28],"been":[29],"reported":[30],"heretofore.":[31],"We":[32],"carry":[33],"out":[34],"here":[35],"a":[36,49,54,58],"full":[37],"performance":[38],"between":[40],"them":[41],"by":[42],"experiments":[43],"on":[44],"various":[45],"document":[46],"collections":[47],"(including":[48],"manually":[50],"word-segmented":[51],"corpus":[52],"golden":[55],"standard),":[56],"semi-quantitative":[59],"to":[61,70],"elucidate":[62],"the":[63],"characteristics":[64],"behavior;":[67],"try":[69],"provide":[71],"some":[72],"preliminary":[73],"clue":[74],"feature":[76],"term":[77],"choice":[78],"(in":[79],"most":[80],"cases,":[81],"better":[84],"than":[85],"words)":[86],"dimensionality":[88],"setting":[89],"systems.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}