{"id":"https://openalex.org/W2035671593","doi":"https://doi.org/10.1145/1008992.1009118","title":"Verifying a Chinese collection for text categorization","display_name":"Verifying a Chinese collection for text categorization","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2035671593","doi":"https://doi.org/10.1145/1008992.1009118","mag":"2035671593"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009118","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5050118459","display_name":"Yuen\u2010Hsien Tseng","orcid":"https://orcid.org/0000-0001-8904-7902"},"institutions":[{"id":"https://openalex.org/I114150738","display_name":"Fu Jen Catholic University","ror":"https://ror.org/04je98850","country_code":"TW","type":"education","lineage":["https://openalex.org/I114150738"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yuen-Hsien Tseng","raw_affiliation_strings":["Fu Jen Catholic University, Taipei, Taiwan","Fu Jen Catholic University,Taipei, Taiwan#TAB#"],"affiliations":[{"raw_affiliation_string":"Fu Jen Catholic University, Taipei, Taiwan","institution_ids":["https://openalex.org/I114150738"]},{"raw_affiliation_string":"Fu Jen Catholic University,Taipei, Taiwan#TAB#","institution_ids":["https://openalex.org/I114150738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025875274","display_name":"William J. Teahan","orcid":"https://orcid.org/0000-0003-3640-6750"},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William John Teahan","raw_affiliation_strings":["","Bangor University"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Bangor University","institution_ids":["https://openalex.org/I161548249"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050118459"],"corresponding_institution_ids":["https://openalex.org/I114150738"],"apc_list":null,"apc_paid":null,"fwci":0.2759,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5945671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"556","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.998199999332428,"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":0.9972000122070312,"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/categorization","display_name":"Categorization","score":0.8299494385719299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8021050095558167},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7105166912078857},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5904114246368408},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.5635958909988403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5446405410766602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4650982618331909}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8299494385719299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021050095558167},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7105166912078857},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5904114246368408},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.5635958909988403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5446405410766602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650982618331909},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1008992.1009118","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.581.7671","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.581.7671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.ntnu.edu.tw/~samtseng/papers/p556-tseng.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.895.799","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.895.799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Yuen-Hsien_Tseng/publication/221300549_Verifying_a_Chinese_collection_for_text_categorization/links/02bfe50fcc2eec3d79000000.pdf?origin%3Dpublication_detail","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.907.1738","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.907.1738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Yuen-Hsien_Tseng/publication/221300549_Verifying_a_Chinese_collection_for_text_categorization/links/02bfe50fcc2eec3d79000000.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1765388594","https://openalex.org/W1974927094","https://openalex.org/W2014415866"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"the":[3,64],"development":[4],"of":[5,42],"a":[6],"free":[7],"test":[8],"collection":[9],"for":[10,32],"Chinese":[11],"text":[12],"categorization.":[13],"A":[14],"novel":[15],"retrieval-based":[16],"approach":[17],"was":[18,36,60],"developed":[19],"to":[20,38],"detect":[21,39],"duplicates":[22],"and":[23,29],"label":[24],"inconsistency":[25],"in":[26,30],"this":[27],"corpus":[28],"Reuters-21578":[31],"comparison.":[33],"The":[34],"method":[35,54],"able":[37],"certain":[40],"types":[41],"similar":[43],"and/or":[44],"duplicated":[45],"documents":[46],"that":[47,58],"were":[48],"overlooked":[49],"by":[50,63],"an":[51],"alternative":[52],"repetition-based":[53],"[1].":[55],"Experiments":[56],"showed":[57],"effectiveness":[59],"not":[61],"affected":[62],"confusing":[65],"documents.":[66]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
