{"id":"https://openalex.org/W2163786136","doi":null,"title":"Enhanced classification through exploitation of hierarchical structures","display_name":"Enhanced classification through exploitation of hierarchical structures","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2163786136","mag":"2163786136"},"language":"en","primary_location":{"id":"mag:2163786136","doi":null,"is_oa":false,"landing_page_url":"https://repositories.lib.utexas.edu/bitstream/2152/3265/2/punerak87642.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5103071668","display_name":"Joydeep Ghosh","orcid":"https://orcid.org/0000-0002-7366-3548","observed_orcids":["https://orcid.org/0000-0002-7366-3548"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joydeep Ghosh","raw_affiliation_strings":["the University of Texas at, Austin"],"raw_orcid":"https://orcid.org/0000-0002-7366-3548","affiliations":[{"raw_affiliation_string":"the University of Texas at, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089487172","display_name":"Kunal Punera","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Punera","raw_affiliation_strings":["the University of Texas at, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the University of Texas at, Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9448000192642212,"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":0.9448000192642212,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.041099999099969864,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/hierarchical-classification","display_name":"hierarchical classification","score":0.9350000023841858},{"id":"https://openalex.org/keywords/taxonomy-general-classification-scheme","display_name":"taxonomy (general classification scheme)","score":0.746999979019165},{"id":"https://openalex.org/keywords/isotonic-regression","display_name":"isotonic regression","score":0.734000027179718},{"id":"https://openalex.org/keywords/rooted-trees","display_name":"rooted trees","score":0.5799999833106995},{"id":"https://openalex.org/keywords/template-detection","display_name":"template detection","score":0.550000011920929},{"id":"https://openalex.org/keywords/web-page-segmentation","display_name":"web page segmentation","score":0.625},{"id":"https://openalex.org/keywords/dom-tree","display_name":"DOM tree","score":0.5450000166893005},{"id":"https://openalex.org/keywords/hierarchical-relationships","display_name":"hierarchical relations","score":0.3630000054836273},{"id":"https://openalex.org/keywords/penalized-regression","display_name":"penalized regression","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7415874004364014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402211427688599},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.6262232661247253},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5974544286727905},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5746661424636841},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5369299650192261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5070662498474121},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4420575499534607},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42220473289489746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3887084424495697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3464627265930176},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/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":1,"locations":[{"id":"mag:2163786136","doi":null,"is_oa":false,"landing_page_url":"https://repositories.lib.utexas.edu/bitstream/2152/3265/2/punerak87642.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":138,"referenced_works":["https://openalex.org/W49486804","https://openalex.org/W178180052","https://openalex.org/W180238871","https://openalex.org/W1484743740","https://openalex.org/W1490760466","https://openalex.org/W1493526108","https://openalex.org/W1502424938","https://openalex.org/W1503141391","https://openalex.org/W1510526001","https://openalex.org/W1522292060","https://openalex.org/W1523949738","https://openalex.org/W1538524459","https://openalex.org/W1550206324","https://openalex.org/W1559013041","https://openalex.org/W1570978137","https://openalex.org/W1574845294","https://openalex.org/W1578372979","https://openalex.org/W1588401315","https://openalex.org/W1592327732","https://openalex.org/W1602492977","https://openalex.org/W1606091631","https://openalex.org/W1620204465","https://openalex.org/W1636244751","https://openalex.org/W1673310716","https://openalex.org/W1676820704","https://openalex.org/W1686946872","https://openalex.org/W1699498167","https://openalex.org/W1909864473","https://openalex.org/W1965490077","https://openalex.org/W1965555277","https://openalex.org/W1971784203","https://openalex.org/W1979032160","https://openalex.org/W1984953641","https://openalex.org/W1989338554","https://openalex.org/W1995233974","https://openalex.org/W1999059106","https://openalex.org/W2002932921","https://openalex.org/W2005124845","https://openalex.org/W2006476860","https://openalex.org/W2006560229","https://openalex.org/W2012161809","https://openalex.org/W2012514949","https://openalex.org/W2014566476","https://openalex.org/W2019363670","https://openalex.org/W2020842694","https://openalex.org/W2031841099","https://openalex.org/W2038959058","https://openalex.org/W2040075907","https://openalex.org/W2040672759","https://openalex.org/W2040870580","https://openalex.org/W2046314114","https://openalex.org/W2049633694","https://openalex.org/W2052142057","https://openalex.org/W2053606794","https://openalex.org/W2063862666","https://openalex.org/W2064818667","https://openalex.org/W2065168033","https://openalex.org/W2066680326","https://openalex.org/W2072489225","https://openalex.org/W2076008912","https://openalex.org/W2078288474","https://openalex.org/W2083598336","https://openalex.org/W2088906645","https://openalex.org/W2090634555","https://openalex.org/W2095897464","https://openalex.org/W2096765209","https://openalex.org/W2097089247","https://openalex.org/W2097645701","https://openalex.org/W2100445067","https://openalex.org/W2100990314","https://openalex.org/W2101711129","https://openalex.org/W2102524069","https://openalex.org/W2103723258","https://openalex.org/W2105842272","https://openalex.org/W2107008379","https://openalex.org/W2107496976","https://openalex.org/W2109760176","https://openalex.org/W2111446078","https://openalex.org/W2112104357","https://openalex.org/W2113709557","https://openalex.org/W2115082394","https://openalex.org/W2115620960","https://openalex.org/W2117209866","https://openalex.org/W2122465391","https://openalex.org/W2124436456","https://openalex.org/W2124776405","https://openalex.org/W2125055259","https://openalex.org/W2125282628","https://openalex.org/W2126631147","https://openalex.org/W2126751256","https://openalex.org/W2127218421","https://openalex.org/W2131687179","https://openalex.org/W2131840460","https://openalex.org/W2132827946","https://openalex.org/W2133814403","https://openalex.org/W2133864802","https://openalex.org/W2136280642","https://openalex.org/W2137079713","https://openalex.org/W2138570191","https://openalex.org/W2138583748","https://openalex.org/W2140209831","https://openalex.org/W2140628095","https://openalex.org/W2141585940","https://openalex.org/W2142132842","https://openalex.org/W2143516773","https://openalex.org/W2143774317","https://openalex.org/W2145001205","https://openalex.org/W2146077059","https://openalex.org/W2146486820","https://openalex.org/W2146855196","https://openalex.org/W2146990843","https://openalex.org/W2148572968","https://openalex.org/W2148781711","https://openalex.org/W2149706766","https://openalex.org/W2152565070","https://openalex.org/W2153662613","https://openalex.org/W2154122057","https://openalex.org/W2154484245","https://openalex.org/W2155942458","https://openalex.org/W2156523427","https://openalex.org/W2157108978","https://openalex.org/W2157748587","https://openalex.org/W2160560153","https://openalex.org/W2160586919","https://openalex.org/W2160642098","https://openalex.org/W2163614729","https://openalex.org/W2164052363","https://openalex.org/W2167859982","https://openalex.org/W2169189540","https://openalex.org/W2170040807","https://openalex.org/W2170478283","https://openalex.org/W2172023103","https://openalex.org/W2293457282","https://openalex.org/W2751862591","https://openalex.org/W2766736793","https://openalex.org/W2946686878","https://openalex.org/W2949219489","https://openalex.org/W2997295514"],"related_works":["https://openalex.org/W7097038055","https://openalex.org/W80896490","https://openalex.org/W2115620960","https://openalex.org/W7098497961","https://openalex.org/W7097143017","https://openalex.org/W7099960116","https://openalex.org/W7095679311","https://openalex.org/W2073830447","https://openalex.org/W2358717065","https://openalex.org/W7095589984"],"abstract_inverted_index":{"Humans":[0],"often":[1],"organize":[2],"information":[3,134],"by":[4],"encoding":[5],"it":[6,276,319],"in":[7,136,221,271,384,418],"structures":[8,22,188],"that":[9,38,84,108,132,148,218,264,281,324],"link":[10],"together":[11],"entities":[12,113],"such":[13],"as":[14,91,153,353,376,378],"concepts,":[15],"objects,":[16],"properties":[17],"etc.":[18],"Among":[19],"the":[20,51,94,101,133,159,176,195,201,204,228,252,283,290,294,304,335,343,349,366,374,379,387,402,416],"various":[21],"possible,":[23],"hierarchies":[24,35,138],"are":[25,55,63,67,82,230,363],"commonly":[26,33],"used.":[27],"For":[28,391],"instance,":[29],"taxonomies":[30,60,229],"of":[31,44,58,80,100,161,178,197,203,246,254,259,268,273,285,298,306,322,345,351,365,373,386,412,415],"categories":[32],"employ":[34],"to":[36,70,98,117,142,157,211,237,333,399],"indicate":[37],"one":[39],"category":[40],"is":[382],"a":[154,243,269,315,320],"type":[43],"another.":[45],"The":[46,371],"Yahoo!":[47],"Web":[48],"Directory":[49,53],"and":[50,88,167,216,317,328,408],"Open":[52],"Project":[54],"two":[56],"examples":[57],"large":[59],"where":[61,93,227],"topics":[62],"hierarchically":[64],"arranged.":[65],"Hierarchies":[66],"also":[68],"used":[69],"recursively":[71],"decompose":[72],"composite":[73],"objects":[74],"into":[75,180,192,309],"their":[76],"constituent":[77],"parts.":[78],"Examples":[79],"this":[81,104,219,339,419],"webpages":[83],"can":[85,114,139,149,189],"be":[86,115,140,151,190,411],"parsed":[87],"then":[89,150],"represented":[90],"DOM-trees,":[92],"DOM":[95],"nodes":[96,202],"correspond":[97],"sections":[99],"webpages.":[102,260],"\r\nIn":[103],"thesis":[105],"we":[106,130,174,208,233,249,279,302,395],"argue":[107],"these":[109,137,214,286,362,393],"hierarchical":[110,181,240],"relationships":[111,241],"between":[112],"exploited":[116],"facilitate":[118],"common":[119],"data":[120],"mining":[121],"tasks":[122],"defined":[123],"upon":[124],"them,":[125],"like":[126],"automated":[127],"classification.":[128,162],"Specifically,":[129],"show":[131,184,217,280],"encoded":[135],"reduced":[141],"constraints":[143,193,215,347,375],"on":[144,169,194,251,348,359],"class":[145],"membership":[146],"scores":[147],"enforced":[152],"post-processing":[155],"step":[156],"enhance":[158],"accuracy":[160],"We":[163,183,261,313],"demonstrate":[164],"our":[165,299],"ideas":[166],"algorithms":[168,210,263,398,409],"three":[170],"real-world":[171],"tasks.":[172],"\r\nFirst,":[173],"tackle":[175],"problem":[177,253,344],"classification":[179,223],"taxonomies.":[182],"how":[185,274],"different":[186,383],"taxonomy":[187],"translated":[191],"outputs":[196,350],"classifiers":[198,288,352],"learned":[199],"at":[200],"hierarchy.":[205],"In":[206,225],"addition,":[207],"give":[209,234,262,329,396],"optimally":[212,400],"enforce":[213],"results":[220],"improved":[222],"accuracy.":[224],"cases":[226],"not":[231],"available,":[232],"an":[235,330],"approach":[236],"automatically":[238],"derive":[239],"amongst":[242],"flat":[244],"set":[245,321],"categories.":[247],"Next,":[248],"work":[250],"detecting":[255],"noisy":[256],"(templated)":[257],"parts":[258],"rate":[265],"each":[266,385],"section":[267],"webpage":[270],"terms":[272],"templated":[275],"is.":[277],"Then":[278],"smoothing":[282],"output":[284],"template":[287,295],"over":[289],"DOM-tree":[291],"hierarchy":[292],"improves":[293],"detection":[296],"performance":[297],"system.":[300],"Finally,":[301],"investigate":[303],"task":[305],"segmenting":[307],"websites":[308],"topically":[310],"cohesive":[311],"regions.":[312],"define":[314],"framework":[316],"within":[318,338],"measures":[323],"characterize":[325],"good":[326],"segmentations,":[327],"efficient":[331,397],"algorithm":[332],"find":[334],"best":[336],"segmentation":[337],"framework.":[340],"\r\nWe":[341],"formalize":[342],"enforcing":[346],"regularized":[354],"isotonic":[355,368],"or":[356],"unimodal":[357],"regression":[358,369],"rooted":[360],"trees;":[361],"generalizations":[364],"classic":[367],"problem.":[370],"nature":[372],"well":[377],"cost":[380],"functions":[381],"applications":[388,417],"mentioned":[389],"above.":[390],"all":[392],"formulations":[394,407],"smooth":[401],"classifier":[403],"outputs.":[404],"These":[405],"novel":[406],"might":[410],"interest":[413],"independent":[414],"thesis.":[420]},"counts_by_year":[],"updated_date":"2026-10-04T09:36:47.201465","created_date":"2016-06-24T00:00:00"}