{"id":"https://openalex.org/W3094448412","doi":"https://doi.org/10.1145/3340531.3412782","title":"Web Page Segmentation Revisited","display_name":"Web Page Segmentation Revisited","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094448412","doi":"https://doi.org/10.1145/3340531.3412782","mag":"3094448412"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & 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/A5037380544","display_name":"Johannes Kiesel","orcid":"https://orcid.org/0000-0002-1617-6508"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Kiesel","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014396215","display_name":"Florian Kneist","orcid":"https://orcid.org/0000-0002-4111-662X"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Kneist","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011901298","display_name":"Lars Meyer","orcid":"https://orcid.org/0000-0002-7280-808X"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Meyer","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076654409","display_name":"Kristof Komlossy","orcid":null},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kristof Komlossy","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benno Stein","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["Leipzig University, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Leipzig University, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037380544"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":2.2253,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90887464,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3047","last_page":"3054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T13976","display_name":"Web visibility and informetrics","score":0.9812999963760376,"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":0.9771999716758728,"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":0.8611637353897095},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7693685293197632},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6447805166244507},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6302462816238403},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5920906662940979},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.5633559226989746},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5436801314353943},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5261192917823792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4337750971317291},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3181847035884857},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19163668155670166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611637353897095},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7693685293197632},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6447805166244507},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6302462816238403},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5920906662940979},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.5633559226989746},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5436801314353943},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5261192917823792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4337750971317291},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3181847035884857},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19163668155670166},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340531.3412782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W28892826","https://openalex.org/W1513638398","https://openalex.org/W1566513354","https://openalex.org/W1971784203","https://openalex.org/W2002238744","https://openalex.org/W2015933107","https://openalex.org/W2020254000","https://openalex.org/W2044958453","https://openalex.org/W2051097555","https://openalex.org/W2057510760","https://openalex.org/W2061783331","https://openalex.org/W2072240081","https://openalex.org/W2084358158","https://openalex.org/W2090193136","https://openalex.org/W2118860332","https://openalex.org/W2121871415","https://openalex.org/W2121927366","https://openalex.org/W2135769635","https://openalex.org/W2145023731","https://openalex.org/W2154484245","https://openalex.org/W2166407869","https://openalex.org/W2171149144","https://openalex.org/W2229908198","https://openalex.org/W2274492630","https://openalex.org/W2328893508","https://openalex.org/W2400661088","https://openalex.org/W2588006593","https://openalex.org/W2746892682","https://openalex.org/W2783946743","https://openalex.org/W2785494106","https://openalex.org/W2806235491","https://openalex.org/W2899042831","https://openalex.org/W2915774443","https://openalex.org/W2969007438","https://openalex.org/W3013810144","https://openalex.org/W3109166473","https://openalex.org/W3140400178","https://openalex.org/W4213245422","https://openalex.org/W4233527139"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"Each":[0],"web":[1,19,32,154,179],"page":[2,20,155],"can":[3,76],"be":[4,77],"segmented":[5],"into":[6],"semantically":[7],"coherent":[8],"units":[9],"that":[10,144],"fulfill":[11],"specific":[12],"purposes.":[13],"Though":[14],"the":[15,41,84,132,165,175],"task":[16],"of":[17,57,124,136,153,168,178],"automatic":[18],"segmentation":[21,85,100,106,134],"was":[22],"introduced":[23],"two":[24,69],"decades":[25],"ago,":[26],"along":[27],"with":[28],"several":[29],"applications":[30],"in":[31],"content":[33],"analysis,":[34],"its":[35],"foundations":[36],"are":[37],"still":[38],"lacking.":[39],"Specifically,":[40],"developed":[42],"evaluation":[43,61,73],"methods":[44],"and":[45,60,90,93,102,159],"datasets":[46,59],"presume":[47],"a":[48,55,171],"certain":[49],"downstream":[50,80],"task,":[51],"which":[52,75,94],"led":[53],"to":[54,79,129],"variety":[56],"incompatible":[58],"methods.":[62],"To":[63],"address":[64],"this":[65],"shortcoming,":[66],"we":[67,142],"contribute":[68],"resources:":[70],"(1)":[71],"An":[72],"framework":[74],"adjusted":[78],"tasks":[81],"by":[82,121],"measuring":[83],"similarity":[86],"regarding":[87,164],"visual,":[88],"structural,":[89,158],"textual":[91],"elements,":[92],"includes":[95],"measures":[96],"for":[97,105,115,150],"annotator":[98],"agreement,":[99],"quality,":[101],"an":[103,122],"algorithm":[104],"fusion.":[107],"(2)":[108],"The":[109],"Webis-WebSeg-20":[110],"dataset,":[111],"comprising":[112],"42,450~crowdsourced":[113],"segmentations":[114,149],"8,490~web":[116],"pages,":[117],"outranging":[118],"existing":[119],"sources":[120],"order":[123],"magnitude.":[125],"Our":[126],"results":[127],"help":[128],"better":[130],"understand":[131],"\"mental":[133],"model''":[135],"human":[137],"annotators:":[138],"Among":[139],"other":[140],"things":[141],"find":[143],"annotators":[145],"mostly":[146,163],"agree":[147],"on":[148,174],"all":[151],"kinds":[152],"elements":[156],"(visual,":[157],"textual).":[160],"Disagreement":[161],"exists":[162],"right":[166],"level":[167],"granularity,":[169],"indicating":[170],"general":[172],"agreement":[173],"visual":[176],"structure":[177],"pages.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}