{"id":"https://openalex.org/W2142743398","doi":"https://doi.org/10.1109/isit.2010.5513627","title":"MDL hierarchical clustering for stemmatology","display_name":"MDL hierarchical clustering for stemmatology","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2142743398","doi":"https://doi.org/10.1109/isit.2010.5513627","mag":"2142743398"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2010.5513627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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":false,"raw_author_name":"Po-Hsiang Lai","raw_affiliation_strings":["Electrical and Systems Engineering, Washington University in Saint Louis, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Systems Engineering, Washington University in Saint Louis, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066842476","display_name":"Teemu Roos","orcid":"https://orcid.org/0000-0001-9470-3759"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teemu Roos","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, USA","institution_ids":[]}]},{"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 in Saint Louis, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Systems Engineering, Washington University in Saint Louis, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.551,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":3,"citation_normalized_percentile":{"value":0.702672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":75,"max":77},"biblio":{"volume":null,"issue":null,"first_page":"1403","last_page":"1407"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9989,"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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9989,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9932,"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/minimum-description-length","display_name":"Minimum description length","score":0.7249648},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.4150109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416073},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.7249648},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6085684},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.602914},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5875579},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5639934},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5566385},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4702455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44192725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4176646},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.4150109},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33491653},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2010.5513627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":14,"referenced_works":["https://openalex.org/W1566045017","https://openalex.org/W2034230784","https://openalex.org/W2088930249","https://openalex.org/W2101460669","https://openalex.org/W2102098892","https://openalex.org/W2120083505","https://openalex.org/W2128859735","https://openalex.org/W2147299230","https://openalex.org/W2154334459","https://openalex.org/W2163166770","https://openalex.org/W2952484491","https://openalex.org/W3123545922","https://openalex.org/W55191700","https://openalex.org/W63864240"],"related_works":["https://openalex.org/W775724729","https://openalex.org/W4318471783","https://openalex.org/W4308771405","https://openalex.org/W3080197661","https://openalex.org/W2991781269","https://openalex.org/W2963669501","https://openalex.org/W2760667490","https://openalex.org/W2588206991","https://openalex.org/W2355873265","https://openalex.org/W2137489486"],"abstract_inverted_index":{"In":[0,57,143],"real":[1],"life,":[2],"one":[3,8],"often":[4],"encounters":[5],"situations":[6],"where":[7,32,80],"needs":[9],"to":[10,45,71,83,100,119,173],"infer":[11],"a":[12,109,132,151,160],"structural":[13,73],"relationship":[14],"among":[15,55],"data":[16,85,89],"points":[17,90],"based":[18,112],"on":[19,78,98,113,150],"an":[20],"incomplete":[21],"dataset.":[22,166],"Stemmatology":[23],"and":[24,41,121,130,154,162,170],"phylogenetics":[25],"are":[26,39],"two":[27],"classes":[28],"of":[29,50,65],"such":[30],"problems":[31],"partial":[33],"text":[34],"scripts":[35,51],"or":[36,52],"genome":[37],"sequences":[38],"available":[40,88],"the":[42,47,62,72,87,141],"goal":[43],"is":[44,117],"reconstruct":[46],"copying":[48],"history":[49],"evolutionary":[53],"relations":[54],"species.":[56],"this":[58],"paper,":[59],"we":[60],"study":[61],"potential":[63],"applications":[64],"minimum":[66],"description":[67],"length":[68],"(MDL)":[69],"concepts":[70],"inference":[74],"problem,":[75],"particularly":[76],"focusing":[77],"stemmatology":[79],"in":[81,159],"addition":[82],"missing":[84,92,105],"points,":[86],"have":[91],"values.":[93,106],"We":[94,107,167],"offer":[95],"new":[96],"insights":[97,115],"how":[99],"handle":[101],"these":[102],"issues,":[103],"especially":[104],"develop":[108],"general":[110],"algorithm":[111],"MDL":[114,134],"that":[116],"simple":[118,152],"implement":[120],"can":[122],"be":[123],"used":[124],"along":[125],"with":[126,136],"other":[127],"existing":[128,157],"algorithms,":[129],"propose":[131],"generic":[133],"encoder":[135],"minimal":[137],"assumptions":[138],"made":[139],"about":[140],"data.":[142],"simulations,":[144],"our":[145],"method":[146],"performs":[147],"reasonably":[148],"well":[149],"dataset":[153],"outperforms":[155],"major":[156],"methods":[158],"larger":[161],"much":[163],"more":[164],"realistic":[165],"discuss":[168],"directions":[169],"ongoing":[171],"efforts":[172],"further":[174],"improve":[175],"performance.":[176]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2142743398","counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2024-12-17T12:18:59.461062","created_date":"2016-06-24"}