{"id":"https://openalex.org/W4231582634","doi":"https://doi.org/10.1109/iccp53602.2021.9733492","title":"Using BERT for Multi-Label Multi-Language Web Page Classification","display_name":"Using BERT for Multi-Label Multi-Language Web Page Classification","publication_year":2021,"publication_date":"2021-10-28","ids":{"openalex":"https://openalex.org/W4231582634","doi":"https://doi.org/10.1109/iccp53602.2021.9733492"},"language":"en","primary_location":{"id":"doi:10.1109/iccp53602.2021.9733492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp53602.2021.9733492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Intelligent Computer Communication and Processing (ICCP)","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/A5085863594","display_name":"Codru\u021b-Georgian Artene","orcid":"https://orcid.org/0000-0001-6602-4994"},"institutions":[{"id":"https://openalex.org/I4210108695","display_name":"Gheorghe Asachi Technical University of Ia\u0219i","ror":"https://ror.org/014zxnz40","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210108695"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Codrut-Georgian Artene","raw_affiliation_strings":["\"Gh. Asachi\" Technical University of Ia&#x015F;i,Department of Computers,Ia&#x015F;i,Romania"],"affiliations":[{"raw_affiliation_string":"\"Gh. Asachi\" Technical University of Ia&#x015F;i,Department of Computers,Ia&#x015F;i,Romania","institution_ids":["https://openalex.org/I4210108695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032385315","display_name":"Marius Nicolae Tibeic\u0103","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marius Nicolae Tibeica","raw_affiliation_strings":["Cloud Services and Infrastructure Unit Bitdefender,Ia&#x015F;i,Romania"],"affiliations":[{"raw_affiliation_string":"Cloud Services and Infrastructure Unit Bitdefender,Ia&#x015F;i,Romania","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063576338","display_name":"Florin Leon","orcid":"https://orcid.org/0000-0002-1370-9145"},"institutions":[{"id":"https://openalex.org/I4210108695","display_name":"Gheorghe Asachi Technical University of Ia\u0219i","ror":"https://ror.org/014zxnz40","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210108695"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Florin Leon","raw_affiliation_strings":["\"Gh. Asachi\" Technical University of Ia&#x015F;i,Department of Computers,Ia&#x015F;i,Romania"],"affiliations":[{"raw_affiliation_string":"\"Gh. Asachi\" Technical University of Ia&#x015F;i,Department of Computers,Ia&#x015F;i,Romania","institution_ids":["https://openalex.org/I4210108695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085863594"],"corresponding_institution_ids":["https://openalex.org/I4210108695"],"apc_list":null,"apc_paid":null,"fwci":0.98772503,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80926767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.8737965822219849},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7891613245010376},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5223571062088013},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5099884271621704},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5043178796768188},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.47925329208374023},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.47458338737487793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46750932931900024},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.44594162702560425},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.41733038425445557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36707040667533875},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.35091716051101685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8737965822219849},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7891613245010376},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5223571062088013},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5099884271621704},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5043178796768188},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.47925329208374023},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.47458338737487793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46750932931900024},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.44594162702560425},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.41733038425445557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36707040667533875},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.35091716051101685}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp53602.2021.9733492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp53602.2021.9733492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2059586463","https://openalex.org/W2182824764","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2970854433","https://openalex.org/W2972842086","https://openalex.org/W2978017171","https://openalex.org/W2980508402","https://openalex.org/W2996428491","https://openalex.org/W2999962654","https://openalex.org/W3146289447","https://openalex.org/W3149839962","https://openalex.org/W3154224177","https://openalex.org/W3156333129","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6767489872","https://openalex.org/W6768021236","https://openalex.org/W6768851824","https://openalex.org/W6769001469"],"related_works":["https://openalex.org/W2167278502","https://openalex.org/W2389737178","https://openalex.org/W2113184419","https://openalex.org/W406631474","https://openalex.org/W1488511360","https://openalex.org/W1593328609","https://openalex.org/W1984640715","https://openalex.org/W2186766522","https://openalex.org/W2120930843","https://openalex.org/W2351876673"],"abstract_inverted_index":{"With":[0],"a":[1,94,99,123],"very":[2,113],"large":[3,84],"and":[4,15,87,151],"constantly":[5],"growing":[6],"number":[7],"of":[8,19,25,41,45,48,77,125,131,160],"web":[9,26,30,49,139,145,163],"pages":[10,27],"available":[11],"on":[12,83,136],"the":[13,17,20,23,42,46,52,75,129,132],"Internet":[14],"considering":[16],"diversity":[18],"topics":[21],"that":[22,80,155],"content":[24,47],"develops,":[28],"automatic":[29,162],"page":[31,140,146,164],"classification":[32,165],"is":[33,101],"becoming":[34],"increasingly":[35],"important.":[36],"The":[37],"text":[38,67,85,116],"represents":[39],"one":[40,152],"main":[43],"components":[44],"pages.":[50],"In":[51,118],"last":[53],"years,":[54],"researchers":[55],"have":[56],"achieved":[57],"state-of-the-art":[58],"results":[59,150],"in":[60,93],"various":[61],"natural":[62],"language":[63,78],"processing":[64],"tasks,":[65],"including":[66],"classification.":[68,117,141],"This":[69],"was":[70],"possible":[71],"mainly":[72],"due":[73],"to":[74,111,127],"development":[76],"models":[79],"are":[81],"trained":[82],"corpora":[86],"afterwards":[88],"fine-tuned":[89],"for":[90,115],"specific":[91],"tasks":[92],"transfer":[95],"learning":[96],"manner.":[97],"Such":[98],"model":[100],"Bidirectional":[102],"Encoder":[103],"Representations":[104],"from":[105],"Transformers":[106],"(BERT),":[107],"which":[108],"has":[109],"proven":[110],"be":[112,158],"effective":[114],"this":[119],"work,":[120],"we":[121],"propose":[122],"series":[124],"experiments":[126],"evaluate":[128],"effectiveness":[130],"pre-trained":[133],"multilingual":[134],"BERT":[135],"multi-label":[137],"multi-language":[138],"Overall,":[142],"our":[143],"proposed":[144],"classifier":[147],"achieves":[148],"competitive":[149],"may":[153],"conclude":[154],"it":[156],"can":[157],"part":[159],"an":[161],"system.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-02-05T00:54:17.221276","created_date":"2025-10-10T00:00:00"}
