{"id":"https://openalex.org/W1494021613","doi":"https://doi.org/10.1007/3-540-45886-7_16","title":"A Hierarchical Model for Clustering and Categorising Documents","display_name":"A Hierarchical Model for Clustering and Categorising Documents","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W1494021613","doi":"https://doi.org/10.1007/3-540-45886-7_16","mag":"1494021613"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-45886-7_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45886-7_16","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/A5014352159","display_name":"\u00c9ric Gaussier","orcid":"https://orcid.org/0000-0002-8858-3233"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"E. Gaussier","raw_affiliation_strings":["Xerox Research Center Europe, 6 Ch. de Maupertuis, F-38240, Meylan, France"],"affiliations":[{"raw_affiliation_string":"Xerox Research Center Europe, 6 Ch. de Maupertuis, F-38240, Meylan, France","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065257553","display_name":"Cyril Goutte","orcid":"https://orcid.org/0000-0003-4939-6555"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Goutte","raw_affiliation_strings":["Xerox Research Center Europe, 6 Ch. de Maupertuis, F-38240, Meylan, France"],"affiliations":[{"raw_affiliation_string":"Xerox Research Center Europe, 6 Ch. de Maupertuis, F-38240, Meylan, France","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085449195","display_name":"Kalpesh Popat","orcid":"https://orcid.org/0000-0002-3818-3717"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Popat","raw_affiliation_strings":["Xerox PARC, 3333 Coyote Hill Rd, 94304, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Xerox PARC, 3333 Coyote Hill Rd, 94304, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082830921","display_name":"Fankai Chen","orcid":"https://orcid.org/0009-0006-6715-4209"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. Chen","raw_affiliation_strings":["Xerox PARC, 3333 Coyote Hill Rd, 94304, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Xerox PARC, 3333 Coyote Hill Rd, 94304, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I173498003"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014352159"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.9608,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.93971332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9973999857902527,"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":0.9973999857902527,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9962999820709229,"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":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.8551138043403625},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7214722633361816},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7048712968826294},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6016959547996521},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.582219660282135},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5720012187957764},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5711100697517395},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5072083473205566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47698885202407837},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46089452505111694},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43261319398880005},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40084901452064514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.055893123149871826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551138043403625},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7214722633361816},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7048712968826294},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6016959547996521},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.582219660282135},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5720012187957764},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5711100697517395},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5072083473205566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47698885202407837},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46089452505111694},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43261319398880005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40084901452064514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.055893123149871826},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/3-540-45886-7_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45886-7_16","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.4660","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.4660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W48554555","https://openalex.org/W1523949738","https://openalex.org/W1572100238","https://openalex.org/W1572659166","https://openalex.org/W1574901103","https://openalex.org/W1612003148","https://openalex.org/W1999337483","https://openalex.org/W2005422315","https://openalex.org/W2025887562","https://openalex.org/W2049633694","https://openalex.org/W2059279601","https://openalex.org/W2107042471","https://openalex.org/W2127314673","https://openalex.org/W2145036943","https://openalex.org/W2147152072","https://openalex.org/W2149684865","https://openalex.org/W2153405201","https://openalex.org/W2163953154","https://openalex.org/W2166023018","https://openalex.org/W2166473218","https://openalex.org/W2166698530","https://openalex.org/W2184026322","https://openalex.org/W2492794003","https://openalex.org/W2882319491","https://openalex.org/W3129711340","https://openalex.org/W4233135949","https://openalex.org/W4233630311","https://openalex.org/W4235768290"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}