{"id":"https://openalex.org/W2007982515","doi":"https://doi.org/10.1109/ita.2010.5454099","title":"MDL hierarchical clustering with incomplete data","display_name":"MDL hierarchical clustering with incomplete data","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2007982515","doi":"https://doi.org/10.1109/ita.2010.5454099","mag":"2007982515"},"language":"en","primary_location":{"id":"doi:10.1109/ita.2010.5454099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2010.5454099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Information Theory and Applications Workshop (ITA)","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/A5113671863","display_name":"Po\u2010Hsiang Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Po-Hsiang Lai","raw_affiliation_strings":["Electrical and Systems Engineering, Washington University of Saint Louis, USA","[Electrical and Systems Engineering, Washington University in Saint Louis]"],"affiliations":[{"raw_affiliation_string":"Electrical and Systems Engineering, Washington University of Saint Louis, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"[Electrical and Systems Engineering, Washington University in Saint Louis]","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044333105","display_name":"Joseph A. O\u2019Sullivan","orcid":"https://orcid.org/0000-0003-1510-4876"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph A. O'Sullivan","raw_affiliation_strings":["Electrical and Systems Engineering, Washington University of Saint Louis, USA","[Electrical and Systems Engineering, Washington University in Saint Louis]"],"affiliations":[{"raw_affiliation_string":"Electrical and Systems Engineering, Washington University of Saint Louis, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"[Electrical and Systems Engineering, Washington University in Saint Louis]","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113671863"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":0.4655,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72671897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9944000244140625,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9944000244140625,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9939000010490417,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9879000186920166,"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":0.653741717338562},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5500789284706116},{"id":"https://openalex.org/keywords/phylogenetics","display_name":"Phylogenetics","score":0.528289794921875},{"id":"https://openalex.org/keywords/tree-of-life","display_name":"Tree of life (biology)","score":0.5181185603141785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47472891211509705},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.46822071075439453},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.46511179208755493},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.45304372906684875},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.43445006012916565},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4320465624332428},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.41483959555625916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4027843475341797},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.34484925866127014},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3238704800605774},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22560784220695496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17285269498825073},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08845207095146179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.653741717338562},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5500789284706116},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.528289794921875},{"id":"https://openalex.org/C124388736","wikidata":"https://www.wikidata.org/wiki/Q3247497","display_name":"Tree of life (biology)","level":4,"score":0.5181185603141785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47472891211509705},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.46822071075439453},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.46511179208755493},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.45304372906684875},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.43445006012916565},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4320465624332428},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.41483959555625916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027843475341797},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.34484925866127014},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3238704800605774},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22560784220695496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17285269498825073},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08845207095146179},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ita.2010.5454099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2010.5454099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.409.1648","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.409.1648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ita.ucsd.edu/workshop/10/files/paper/paper_185.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W63864240","https://openalex.org/W1638203394","https://openalex.org/W2034230784","https://openalex.org/W2068782468","https://openalex.org/W2099111195","https://openalex.org/W2101460669","https://openalex.org/W2102098892","https://openalex.org/W2128859735","https://openalex.org/W2147299230","https://openalex.org/W2154334459","https://openalex.org/W2160832836","https://openalex.org/W2582697902","https://openalex.org/W2952484491","https://openalex.org/W3123545922","https://openalex.org/W4233815609","https://openalex.org/W6602555961","https://openalex.org/W6683470630"],"related_works":["https://openalex.org/W4308771405","https://openalex.org/W2355873265","https://openalex.org/W2963669501","https://openalex.org/W3080197661","https://openalex.org/W4318471783","https://openalex.org/W2760667490","https://openalex.org/W2991781269","https://openalex.org/W775724729","https://openalex.org/W2137489486","https://openalex.org/W2920877280"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,10,13,25,68,77,95],"stemmatology":[3],"is":[4,21,55,105],"to":[5,51,57,63,82,101,107],"reconstruct":[6,64],"a":[7,14,22,108],"family":[8],"tree":[9],"different":[11],"variants":[12,37,49],"text":[15],"resulting":[16],"from":[17],"imperfect":[18],"copying,":[19],"which":[20],"crucial":[23],"part":[24],"textual":[26],"criticism.":[27],"In":[28],"reality,":[29],"historians":[30],"often":[31],"have":[32],"incomplete":[33],"data":[34],"because":[35],"some":[36],"are":[38,44],"not":[39],"yet":[40],"discovered":[41],"and":[42,90,111],"there":[43],"missing":[45],"portions":[46],"in":[47,85],"available":[48],"due":[50],"physical":[52],"damage.":[53],"Stemmatology":[54],"similar":[56],"molecular":[58],"phylogenetics":[59,78],"where":[60],"biologists":[61],"aim":[62],"the":[65,92],"evolutionary":[66],"history":[67],"species":[69],"based":[70],"on":[71],"genetic":[72],"or":[73],"protein":[74],"sequences.":[75],"Adoption":[76],"methods":[79],"has":[80],"lead":[81],"encouraging":[83],"results":[84],"automatic":[86],"stemmatology.":[87,102],"We":[88],"discuss":[89],"demonstrate":[91],"potential":[93],"application":[94],"minimum":[96],"description":[97],"length":[98],"(MDL)":[99],"concepts":[100],"Our":[103],"method":[104],"applied":[106],"realistic":[109],"dataset":[110],"outperforms":[112],"major":[113],"existing":[114],"methods.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
