{"id":"https://openalex.org/W2114970783","doi":"https://doi.org/10.1109/nlpke.2009.5313771","title":"Document representation combining concepts and words in Chinese text categorization","display_name":"Document representation combining concepts and words in Chinese text categorization","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2114970783","doi":"https://doi.org/10.1109/nlpke.2009.5313771","mag":"2114970783"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2009.5313771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2009.5313771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008461757","display_name":"Chao Che","orcid":"https://orcid.org/0000-0003-2978-5430"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Che","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China","Dalian University of technology,Dalian,Liaoning,China)"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of technology,Dalian,Liaoning,China)","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071708918","display_name":"Hong\u2010Fei Teng","orcid":"https://orcid.org/0000-0003-4946-0473"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HongFei Teng","raw_affiliation_strings":["Dalian University of Technology, Dalian, Liaoning, China","Dalian University of technology,Dalian,Liaoning,China)"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Dalian University of technology,Dalian,Liaoning,China)","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008461757"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11925583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9948999881744385,"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":0.9901999831199646,"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/computer-science","display_name":"Computer science","score":0.7909331917762756},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7714058756828308},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.763619065284729},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7044987082481384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6606084704399109},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5578977465629578},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5279616117477417},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5013492107391357},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.42927515506744385},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22676995396614075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909331917762756},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7714058756828308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.763619065284729},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7044987082481384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6606084704399109},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5578977465629578},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5279616117477417},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5013492107391357},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.42927515506744385},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22676995396614075},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2009.5313771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2009.5313771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1568869800","https://openalex.org/W1569168387","https://openalex.org/W1600320866","https://openalex.org/W1731244441","https://openalex.org/W1787261607","https://openalex.org/W1994025487","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2141734078","https://openalex.org/W2165612380","https://openalex.org/W2435251607","https://openalex.org/W4239007182","https://openalex.org/W6634115543","https://openalex.org/W6637672553","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2047139419","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":{"Word-based":[0],"representation":[1,29,79,99],"is":[2,13,57],"widely":[3],"used":[4],"in":[5,59],"text":[6,121],"categorization.":[7],"However,":[8],"performance":[9,113],"of":[10,38,41,48,77,114,117,124,133],"this":[11,23],"approach":[12,44,69],"affected":[14],"by":[15],"the":[16,36,46,51,54,65,75,85,90,94,103,112,128,131],"problems":[17],"derived":[18],"from":[19],"language":[20],"variation.":[21],"In":[22],"paper,":[24],"we":[25],"investigate":[26],"a":[27],"document":[28],"combining":[30],"words":[31],"and":[32,83],"concepts":[33,95],"to":[34,63,73,81,92,110],"integrate":[35],"advantages":[37],"two":[39],"types":[40,116],"representations.":[42],"The":[43,68],"takes":[45],"part":[47],"speech":[49],"as":[50,89],"concept":[52],"for":[53,98],"word":[55,60],"which":[56],"error-prone":[58],"sense":[61],"disambiguation":[62,66],"reduce":[64],"mistakes.":[67],"employs":[70],"three":[71],"ways":[72],"measure":[74],"contributions":[76],"different":[78,115],"forms":[80],"classification":[82],"selects":[84],"most":[86],"productive":[87],"one":[88],"feature":[91],"drop":[93],"not":[96,101],"suitable":[97],"while":[100],"losing":[102],"lexical":[104],"semantic":[105],"information.":[106],"We":[107],"conduct":[108],"experiments":[109],"compare":[111],"representations":[118],"on":[119],"Chinese":[120],"categorization":[122],"corpus":[123],"Fudan":[125],"University.":[126],"And":[127],"results":[129],"confirm":[130],"validity":[132],"our":[134],"combination":[135],"representation.":[136]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}