{"id":"https://openalex.org/W3209193141","doi":"https://doi.org/10.1145/3459637.3482491","title":"WebKE","display_name":"WebKE","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3209193141","doi":"https://doi.org/10.1145/3459637.3482491","mag":"3209193141"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024508481","display_name":"Chenhao Xie","orcid":"https://orcid.org/0000-0002-1399-0352"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhao Xie","raw_affiliation_strings":["Fudan University & Shuyan Technology Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University & Shuyan Technology Inc., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562765","display_name":"Wenhao Huang","orcid":"https://orcid.org/0000-0001-7557-1391"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Huang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075507821","display_name":"Jiaqing Liang","orcid":"https://orcid.org/0000-0003-0670-5602"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Liang","raw_affiliation_strings":["Fudan University & Shuyan Technology Inc., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University & Shuyan Technology Inc., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013969897","display_name":"Chengsong Huang","orcid":"https://orcid.org/0009-0009-1812-4515"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengsong Huang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":["Fudan University & Fudan-Aishu Cognitive Intelligence Joint Research Center, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University & Fudan-Aishu Cognitive Intelligence Joint Research Center, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2211","last_page":"2220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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":0.8924313187599182},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.7478654384613037},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5512502789497375},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5337988138198853},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5110782384872437},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5093148946762085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5050147175788879},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49537503719329834},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4827286899089813},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.4724723994731903},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45212769508361816},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4352527856826782},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.410094678401947},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3754340708255768},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3700862228870392},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3308568000793457},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3198997974395752},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.2647218704223633},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18622294068336487},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1682870090007782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8924313187599182},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.7478654384613037},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5512502789497375},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5337988138198853},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5110782384872437},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5093148946762085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5050147175788879},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49537503719329834},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4827286899089813},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.4724723994731903},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45212769508361816},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4352527856826782},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.410094678401947},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3754340708255768},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3700862228870392},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3308568000793457},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3198997974395752},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2647218704223633},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18622294068336487},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1682870090007782},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3858198338","display_name":null,"funder_award_id":"2020M681173,2021T140124","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1490688894","https://openalex.org/W1553019137","https://openalex.org/W1772106736","https://openalex.org/W2009591769","https://openalex.org/W2016753842","https://openalex.org/W2027864253","https://openalex.org/W2058053171","https://openalex.org/W2080132606","https://openalex.org/W2097874932","https://openalex.org/W2107598941","https://openalex.org/W2132679783","https://openalex.org/W2161861392","https://openalex.org/W2163072729","https://openalex.org/W2167187514","https://openalex.org/W2216972693","https://openalex.org/W2439475996","https://openalex.org/W2516930406","https://openalex.org/W2539469848","https://openalex.org/W2626778328","https://openalex.org/W2739876091","https://openalex.org/W2746326396","https://openalex.org/W2798734500","https://openalex.org/W2896457183","https://openalex.org/W2946628371","https://openalex.org/W2949370368","https://openalex.org/W2951333348","https://openalex.org/W2962913831","https://openalex.org/W2962982640","https://openalex.org/W2964121744","https://openalex.org/W2971105107","https://openalex.org/W2971313059","https://openalex.org/W3006883036","https://openalex.org/W3011574394","https://openalex.org/W3022865886","https://openalex.org/W3034617555","https://openalex.org/W3034862440","https://openalex.org/W3035131649","https://openalex.org/W3081176230","https://openalex.org/W3088409176","https://openalex.org/W3099461227","https://openalex.org/W3104953317","https://openalex.org/W3105966348","https://openalex.org/W3116427155","https://openalex.org/W3176398467"],"related_works":["https://openalex.org/W2042562985","https://openalex.org/W183683573","https://openalex.org/W3021385460","https://openalex.org/W2139931245","https://openalex.org/W842810586","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W4236762297"],"abstract_inverted_index":{"The":[0,121],"World":[1],"Wide":[2],"Web":[3],"contains":[4],"rich":[5],"up-to-date":[6],"information":[7,95],"for":[8,20,69],"knowledge":[9],"graph":[10],"construction.":[11],"However,":[12],"most":[13],"current":[14],"relation":[15],"extraction":[16],"techniques":[17],"are":[18],"designed":[19],"free":[21],"text":[22],"and":[23,64,96],"thus":[24],"do":[25],"not":[26],"handle":[27],"well":[28],"semi-structured":[29],"web":[30,48,80],"content.":[31,81],"In":[32],"this":[33],"paper,":[34],"we":[35],"propose":[36,74],"a":[37,84,118],"novel":[38],"multi-phase":[39],"machine":[40],"reading":[41],"framework,":[42],"called":[43],"WebKE.":[44],"It":[45,82],"processes":[46],"the":[47,79,92,100,110],"content":[49],"on":[50],"different":[51],"granularity":[52],"by":[53,117],"first":[54],"detecting":[55],"areas":[56],"of":[57,102],"interest":[58],"at":[59,126],"DOM":[60],"tree":[61],"node":[62],"level":[63],"then":[65],"extracting":[66],"relational":[67],"triples":[68],"each":[70],"area.":[71],"We":[72],"also":[73],"HTMLBERT":[75],"as":[76],"an":[77],"encoder":[78],"is":[83,124],"pre-trained":[85],"markup":[86],"language":[87],"model":[88],"that":[89,109],"fully":[90],"leverages":[91],"visual":[93],"layout":[94],"DOM-tree":[97],"structure,":[98],"without":[99],"need":[101],"hand":[103],"engineered":[104],"features.":[105],"Experimental":[106],"results":[107],"show":[108],"proposed":[111],"approach":[112],"outperforms":[113],"state-of-":[114],"the-art":[115],"methods":[116],"considerable":[119],"gain.":[120],"source":[122],"code":[123],"available":[125],"https://github.com/redreamality/webke.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-11-08T00:00:00"}