{"id":"https://openalex.org/W1582457487","doi":"https://doi.org/10.1007/11539087_19","title":"Learning Outliers to Refine a Corpus for Chinese Webpage Categorization","display_name":"Learning Outliers to Refine a Corpus for Chinese Webpage Categorization","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1582457487","doi":"https://doi.org/10.1007/11539087_19","mag":"1582457487"},"language":"en","primary_location":{"id":"doi:10.1007/11539087_19","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11539087_19","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5004014436","display_name":"Dingsheng Luo","orcid":"https://orcid.org/0000-0001-6997-3984"},"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":true,"raw_author_name":"Dingsheng Luo","raw_affiliation_strings":["National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772594","display_name":"Xinhao Wang","orcid":"https://orcid.org/0000-0002-0366-7543"},"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":"Xinhao Wang","raw_affiliation_strings":["National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"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":"Xihong Wu","raw_affiliation_strings":["National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112119747","display_name":"Huisheng Chi","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":"Huisheng Chi","raw_affiliation_strings":["National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory on Machine Perception, School of Electronics Engineering & Computer Science, Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004014436"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14992642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9814000129699707,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8343849182128906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155634999275208},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.731381356716156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5999706983566284},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5799829363822937},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.53401118516922},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5300393104553223},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5271798372268677},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4955860376358032},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4604490399360657},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.43061938881874084},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21761193871498108}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8343849182128906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155634999275208},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.731381356716156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5999706983566284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5799829363822937},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.53401118516922},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5300393104553223},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5271798372268677},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4955860376358032},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4604490399360657},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.43061938881874084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21761193871498108},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/11539087_19","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11539087_19","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1540007258","https://openalex.org/W1931284523","https://openalex.org/W1956559956","https://openalex.org/W2005422315","https://openalex.org/W2013657661","https://openalex.org/W2024046085","https://openalex.org/W2063862666","https://openalex.org/W2093717447","https://openalex.org/W2112076978","https://openalex.org/W2114535528","https://openalex.org/W2116296392","https://openalex.org/W2116317530","https://openalex.org/W2149684865","https://openalex.org/W2325227998","https://openalex.org/W2435251607","https://openalex.org/W2440833291","https://openalex.org/W2505312721"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2106892947"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
