{"id":"https://openalex.org/W2041490212","doi":"https://doi.org/10.1145/2063576.2063920","title":"Representing document as dependency graph for document clustering","display_name":"Representing document as dependency graph for document clustering","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2041490212","doi":"https://doi.org/10.1145/2063576.2063920","mag":"2041490212"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","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/A5100776575","display_name":"Yujing Wang","orcid":"https://orcid.org/0000-0002-6334-245X"},"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":"Yujing Wang","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072992613","display_name":"Xiaochuan Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochuan Ni","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102139311","display_name":"Jian-Tao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-Tao Sun","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097240","display_name":"Yunhai Tong","orcid":"https://orcid.org/0000-0001-8735-2516"},"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":"Yunhai Tong","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370699","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0003-4406-2193"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100776575"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.4276,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.71852952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2177","last_page":"2180"},"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing 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"}}],"keywords":[{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7580596208572388},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6800991296768188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6710702776908875},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5980916619300842},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5821270942687988},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.5670684576034546},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5047544240951538},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46211081743240356},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.45268502831459045},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4446829855442047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.423373281955719},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3373868763446808},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29224151372909546},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.15208843350410461},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07489374279975891}],"concepts":[{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7580596208572388},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6800991296768188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6710702776908875},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5980916619300842},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5821270942687988},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.5670684576034546},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5047544240951538},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46211081743240356},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.45268502831459045},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4446829855442047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423373281955719},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3373868763446808},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29224151372909546},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.15208843350410461},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07489374279975891},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1145/2063576.2063920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W81000870","https://openalex.org/W130742730","https://openalex.org/W140467209","https://openalex.org/W143174683","https://openalex.org/W415413372","https://openalex.org/W1508977358","https://openalex.org/W1558788122","https://openalex.org/W1956559956","https://openalex.org/W1970544520","https://openalex.org/W1996640618","https://openalex.org/W2000982728","https://openalex.org/W2013029404","https://openalex.org/W2022980325","https://openalex.org/W2052449326","https://openalex.org/W2067818150","https://openalex.org/W2069429561","https://openalex.org/W2070670538","https://openalex.org/W2092335550","https://openalex.org/W2097417931","https://openalex.org/W2097606805","https://openalex.org/W2100958137","https://openalex.org/W2116031377","https://openalex.org/W2121372777","https://openalex.org/W2123504323","https://openalex.org/W2127042504","https://openalex.org/W2132914434","https://openalex.org/W2137763598","https://openalex.org/W2140942285","https://openalex.org/W2141465109","https://openalex.org/W2158266063","https://openalex.org/W2158874082","https://openalex.org/W2165612380","https://openalex.org/W2528833921","https://openalex.org/W2963673689","https://openalex.org/W3006668266","https://openalex.org/W3139328003","https://openalex.org/W4256424005"],"related_works":["https://openalex.org/W96331545","https://openalex.org/W1548907175","https://openalex.org/W2583658747","https://openalex.org/W1882920571","https://openalex.org/W1517600056","https://openalex.org/W2159942118","https://openalex.org/W193772702","https://openalex.org/W2003608043","https://openalex.org/W2036633468","https://openalex.org/W2160738675"],"abstract_inverted_index":{"In":[0,32,50],"traditional":[1],"clustering":[2,153],"methods,":[3],"a":[4,37,58],"document":[5,21,54,136,152,167],"is":[6,55,91],"often":[7],"represented":[8,56],"as":[9,57,71],"\"bag":[10],"of":[11,73,85,98,123],"words\"":[12],"(in":[13,18],"BOW":[14,162],"model)":[15,22],"or":[16],"n-grams":[17],"suffix":[19,165],"tree":[20,166],"without":[23],"considering":[24],"the":[25,30,62,74,77,81,95,108,113,120,144,161],"natural":[26],"language":[27],"relationships":[28],"between":[29,83],"words.":[31,86],"this":[33,48],"paper,":[34],"we":[35],"propose":[36],"novel":[38],"approach":[39],"DGDC":[40,145],"(Dependency":[41],"Graph-based":[42],"Document":[43],"Clustering":[44,117],"algorithm)":[45],"to":[46,65,93],"address":[47],"issue.":[49],"our":[51],"algorithm,":[52,119],"each":[53],"dependency":[59,104],"graph":[60],"where":[61],"nodes":[63],"correspond":[64],"words":[66],"which":[67],"can":[68,125,147],"be":[69,126],"seen":[70],"meta-descriptions":[72],"document;":[75],"whereas":[76],"edges":[78],"stand":[79],"for":[80],"relations":[82],"pairs":[84],"A":[87],"new":[88,109],"similarity":[89,97,110],"measure":[90,111],"proposed":[92],"compute":[94],"pairwise":[96],"documents":[99,124],"based":[100,159],"on":[101,133,160],"their":[102],"corresponding":[103],"graphs.":[105],"By":[106],"applying":[107],"in":[112,151],"Group-average":[114],"Agglomerative":[115],"Hierarchial":[116],"(GAHC)":[118],"final":[121],"clusters":[122],"obtained.":[127],"The":[128,138],"experiments":[129],"were":[130],"carried":[131],"out":[132],"five":[134],"public":[135],"datasets.":[137],"empirical":[139],"results":[140],"have":[141],"indicated":[142],"that":[143],"algorithm":[146],"achieve":[148],"better":[149],"performance":[150],"tasks":[154],"compared":[155],"with":[156],"other":[157],"approaches":[158],"model":[163],"and":[164],"model.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}