{"id":"https://openalex.org/W2106592096","doi":"https://doi.org/10.1017/s1351324914000023","title":"A tree-based learning approach for document structure analysis and its application to web search","display_name":"A tree-based learning approach for document structure analysis and its application to web search","publication_year":2014,"publication_date":"2014-02-24","ids":{"openalex":"https://openalex.org/W2106592096","doi":"https://doi.org/10.1017/s1351324914000023","mag":"2106592096"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324914000023","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324914000023","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-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/A5021327472","display_name":"F. Canan Pembe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141511","display_name":"TUBITAK BILGEM","ror":"https://ror.org/057kvja37","country_code":"TR","type":"government","lineage":["https://openalex.org/I4210141511"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"F. CANAN PEMBE","raw_affiliation_strings":["T\u00dcB\u0130TAK B\u0130LGEM, 41470, Gebze, Kocaeli, Turkey e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00dcB\u0130TAK B\u0130LGEM, 41470, Gebze, Kocaeli, Turkey e-mail:","institution_ids":["https://openalex.org/I4210141511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030496360","display_name":"Tunga G\u00fcng\u00f6r","orcid":"https://orcid.org/0000-0001-9448-9422"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"TUNGA G\u00dcNG\u00d6R","raw_affiliation_strings":["Department of Computer Engineering, Bo\u011fazi\u00e7i University, \u0130stanbul, 34342, Turkey e-mail:","Bo\u011fazi\u00e7i University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bo\u011fazi\u00e7i University, \u0130stanbul, 34342, Turkey e-mail:","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Bo\u011fazi\u00e7i University","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.1976997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"4","first_page":"569","last_page":"605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9966999888420105,"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":0.9800000190734863,"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":0.8864856958389282},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6943619251251221},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5533148646354675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5513060092926025},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5395371913909912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5154569745063782},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4933291971683502},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4871313273906708},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.44302308559417725},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4413915276527405},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4323711693286896},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4228942096233368},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4209215044975281},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12373748421669006},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.11639571189880371}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8864856958389282},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6943619251251221},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5533148646354675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5513060092926025},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5395371913909912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5154569745063782},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4933291971683502},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4871313273906708},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.44302308559417725},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4413915276527405},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4323711693286896},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4228942096233368},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4209215044975281},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12373748421669006},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.11639571189880371},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324914000023","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324914000023","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W44107710","https://openalex.org/W75850408","https://openalex.org/W84307560","https://openalex.org/W100562005","https://openalex.org/W140467209","https://openalex.org/W218853445","https://openalex.org/W567631018","https://openalex.org/W1490960179","https://openalex.org/W1540550673","https://openalex.org/W1549656520","https://openalex.org/W1554944419","https://openalex.org/W1555659003","https://openalex.org/W1576520375","https://openalex.org/W1581477759","https://openalex.org/W1597521809","https://openalex.org/W1602839414","https://openalex.org/W1604938182","https://openalex.org/W1618905105","https://openalex.org/W1660390307","https://openalex.org/W1766594731","https://openalex.org/W1965995882","https://openalex.org/W1966006379","https://openalex.org/W1967359578","https://openalex.org/W1976050545","https://openalex.org/W2012575882","https://openalex.org/W2018117515","https://openalex.org/W2022106151","https://openalex.org/W2028009320","https://openalex.org/W2076832658","https://openalex.org/W2078802887","https://openalex.org/W2078951877","https://openalex.org/W2079525773","https://openalex.org/W2082884138","https://openalex.org/W2095680579","https://openalex.org/W2095818033","https://openalex.org/W2101075799","https://openalex.org/W2104917081","https://openalex.org/W2107394387","https://openalex.org/W2122037382","https://openalex.org/W2130698435","https://openalex.org/W2135036692","https://openalex.org/W2139005824","https://openalex.org/W2145907631","https://openalex.org/W2147428516","https://openalex.org/W2147466442","https://openalex.org/W2154547898","https://openalex.org/W2155869763","https://openalex.org/W2158342607","https://openalex.org/W2169419880","https://openalex.org/W2302382203","https://openalex.org/W2599337667","https://openalex.org/W2604738573","https://openalex.org/W2610930722","https://openalex.org/W2751318774","https://openalex.org/W2787894218","https://openalex.org/W2914756598","https://openalex.org/W3151369355","https://openalex.org/W4229537344","https://openalex.org/W4230683138","https://openalex.org/W4233402780","https://openalex.org/W4239510350","https://openalex.org/W4247119837","https://openalex.org/W4249362488","https://openalex.org/W4255790188","https://openalex.org/W4396706831"],"related_works":["https://openalex.org/W2093597205","https://openalex.org/W2389846579","https://openalex.org/W2392495745","https://openalex.org/W132250100","https://openalex.org/W2725657302","https://openalex.org/W2170202678","https://openalex.org/W2355247546","https://openalex.org/W1987947616","https://openalex.org/W2133814403","https://openalex.org/W1555822132"],"abstract_inverted_index":{"Abstract":[0],"In":[1,23],"this":[2,74],"paper,":[3],"we":[4,76],"study":[5],"the":[6,17,98,101,137,143,152,160,185,189],"problem":[7,62],"of":[8,11,20,33,100,145,154,159,178,191],"structural":[9],"analysis":[10],"Web":[12,155],"documents":[13],"aiming":[14],"at":[15],"extracting":[16],"sectional":[18],"hierarchy":[19,32,52,71,104],"a":[21,25,31,60,64,109,132],"document.":[22],"general,":[24],"document":[26,121,146],"can":[27],"be":[28],"represented":[29],"as":[30,59],"sections":[34],"and":[35,40,51,87,103,119,180,183],"subsections":[36],"with":[37,95],"corresponding":[38],"headings":[39],"subheadings.":[41],"We":[42,140],"developed":[43,77],"two":[44],"machine":[45,127],"learning":[46,66,80,128],"models:":[47],"heading":[48,102],"extraction":[49,53,56,105],"model":[50,123],"model.":[54],"Heading":[55],"was":[57,68,113],"formulated":[58],"classification":[61],"whereas":[63],"tree-based":[65],"approach":[67,112],"employed":[69],"in":[70,93,151,176],"extraction.":[72],"For":[73,107],"purpose,":[75],"an":[78],"incremental":[79],"algorithm":[81],"based":[82],"on":[83,117,148,163],"support":[84],"vector":[85],"machines":[86],"perceptrons.":[88],"The":[89,126,157],"models":[90],"were":[91],"evaluated":[92],"detail":[94],"respect":[96],"to":[97,172,187],"performance":[99],"tasks.":[106],"comparison,":[108],"baseline":[110],"rule-based":[111,138],"used":[114],"that":[115,167],"relies":[116],"heuristics":[118],"HTML":[120],"object":[122],"tree":[124],"processing.":[125],"approach,":[129,135],"which":[130],"is":[131],"fully":[133],"automatic":[134,149],"outperformed":[136],"approach.":[139],"also":[141],"analyzed":[142],"effect":[144],"structuring":[147],"summarization":[150],"context":[153],"search.":[156],"results":[158,193],"task-based":[161],"evaluation":[162],"TREC":[164],"queries":[165],"showed":[166],"structured":[168],"summaries":[169,174],"are":[170],"superior":[171],"unstructured":[173],"both":[175],"terms":[177],"accuracy":[179],"user":[181],"ratings,":[182],"enable":[184],"users":[186],"determine":[188],"relevancy":[190],"search":[192,197],"more":[194],"accurately":[195],"than":[196],"engine":[198],"snippets.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}