{"id":"https://openalex.org/W4321457507","doi":"https://doi.org/10.1017/s1351324923000049","title":"An unsupervised perplexity-based method for boilerplate removal","display_name":"An unsupervised perplexity-based method for boilerplate removal","publication_year":2023,"publication_date":"2023-02-21","ids":{"openalex":"https://openalex.org/W4321457507","doi":"https://doi.org/10.1017/s1351324923000049"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324923000049","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000049","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/5E589D838F1D1E0736B4F52001150339/S1351324923000049a.pdf/div-class-title-an-unsupervised-perplexity-based-method-for-boilerplate-removal-div.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/5E589D838F1D1E0736B4F52001150339/S1351324923000049a.pdf/div-class-title-an-unsupervised-perplexity-based-method-for-boilerplate-removal-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088247071","display_name":"Marcos Fern\u00e1ndez-Pichel","orcid":"https://orcid.org/0000-0002-6560-9832"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Marcos Fern\u00e1ndez-Pichel","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain"],"raw_orcid":"https://orcid.org/0000-0002-6560-9832","affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102818190","display_name":"Manuel Prada-Corral","orcid":"https://orcid.org/0000-0003-2731-079X"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel Prada-Corral","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain"],"raw_orcid":"https://orcid.org/0000-0003-2731-079X","affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020247368","display_name":"David E. Losada","orcid":"https://orcid.org/0000-0001-8823-7501"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David E. Losada","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain"],"raw_orcid":"https://orcid.org/0000-0001-8823-7501","affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007913294","display_name":"Juan C. Pichel","orcid":"https://orcid.org/0000-0001-9505-6493"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan C. Pichel","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain"],"raw_orcid":"https://orcid.org/0000-0001-9505-6493","affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063153446","display_name":"Pablo Gamallo","orcid":"https://orcid.org/0000-0002-5819-2469"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Gamallo","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain"],"raw_orcid":"https://orcid.org/0000-0002-5819-2469","affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnoloxas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782 Santiago de Compostela, Galicia (Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088247071"],"corresponding_institution_ids":["https://openalex.org/I200284239","https://openalex.org/I4210111807"],"apc_list":null,"apc_paid":null,"fwci":1.269,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82268506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"30","issue":"1","first_page":"132","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.900123119354248},{"id":"https://openalex.org/keywords/boilerplate-text","display_name":"Boilerplate text","score":0.888981819152832},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8627004623413086},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6875252723693848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5111022591590881},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4759920835494995},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44936126470565796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44055530428886414},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4227159321308136},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.412209153175354},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39243823289871216},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34853342175483704},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1288236677646637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.900123119354248},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.888981819152832},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8627004623413086},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6875252723693848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5111022591590881},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4759920835494995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44936126470565796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44055530428886414},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4227159321308136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.412209153175354},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39243823289871216},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34853342175483704},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1288236677646637},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":2,"locations":[{"id":"doi:10.1017/s1351324923000049","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000049","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/5E589D838F1D1E0736B4F52001150339/S1351324923000049a.pdf/div-class-title-an-unsupervised-perplexity-based-method-for-boilerplate-removal-div.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:minerva.usc.es:10347/30368","is_oa":true,"landing_page_url":"http://hdl.handle.net/10347/30368","pdf_url":"https://minerva.usc.es/bitstreams/48131060-4a60-4954-965b-f463a21d8d4c/download","source":{"id":"https://openalex.org/S4306400376","display_name":"Repositorio institucional da Universidade de Santiago de Compostela (University of Santiago de Compostela)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200284239","host_organization_name":"Universidade de Santiago de Compostela","host_organization_lineage":["https://openalex.org/I200284239"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1017/s1351324923000049","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000049","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/5E589D838F1D1E0736B4F52001150339/S1351324923000049a.pdf/div-class-title-an-unsupervised-perplexity-based-method-for-boilerplate-removal-div.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G121809054","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G1218400627","display_name":null,"funder_award_id":"2019-2022","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G1869016439","display_name":null,"funder_award_id":"2019-2022","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2309174360","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3694284866","display_name":null,"funder_award_id":"ED431C","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G451917667","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5421974903","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G5544429559","display_name":null,"funder_award_id":"PLEC2021-007662","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G5550858994","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G5967599077","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6206803543","display_name":null,"funder_award_id":"2019-2022 ED431G-2019/04","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6558061132","display_name":null,"funder_award_id":"MCIN/AEI/10.","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G6689507146","display_name":null,"funder_award_id":"ED431G-2019/04","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7535663061","display_name":null,"funder_award_id":"AEI/10.","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8055432103","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G8872346354","display_name":null,"funder_award_id":"MCIN/AEI/10.13039","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320328802","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4321457507.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W68441731","https://openalex.org/W116870935","https://openalex.org/W1989338554","https://openalex.org/W2067223933","https://openalex.org/W2072489225","https://openalex.org/W2084929085","https://openalex.org/W2093390569","https://openalex.org/W2120101509","https://openalex.org/W2122246425","https://openalex.org/W2137698233","https://openalex.org/W2151588647","https://openalex.org/W2155364607","https://openalex.org/W2160709761","https://openalex.org/W2578576916","https://openalex.org/W2613895792","https://openalex.org/W2733060938","https://openalex.org/W2740559467","https://openalex.org/W2899154813","https://openalex.org/W2914164530","https://openalex.org/W2962753212","https://openalex.org/W2964079897","https://openalex.org/W2965373594","https://openalex.org/W2991535285","https://openalex.org/W3021347373","https://openalex.org/W3102354094","https://openalex.org/W3158689111","https://openalex.org/W3214897310","https://openalex.org/W4251504464","https://openalex.org/W4310492983","https://openalex.org/W4385245566","https://openalex.org/W4399196359","https://openalex.org/W6600000387","https://openalex.org/W6739901393","https://openalex.org/W6741080416","https://openalex.org/W6773953490","https://openalex.org/W6776225533"],"related_works":["https://openalex.org/W1989705153","https://openalex.org/W2496228846","https://openalex.org/W2896411932","https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4225161397"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"availability":[2],"of":[3,16,48,81,107,114,118,143,173],"large":[4],"web-based":[5],"corpora":[6],"has":[7],"led":[8],"to":[9,68,122],"significant":[10],"advances":[11],"in":[12,105,135],"a":[13,63,99,112,154,160,167],"wide":[14],"range":[15],"technologies,":[17],"including":[18],"massive":[19],"retrieval":[20],"systems":[21],"or":[22,43,55,125],"deep":[23],"neural":[24],"networks.":[25],"However,":[26],"leveraging":[27],"this":[28,59],"data":[29],"is":[30,35,98],"challenging,":[31],"since":[32],"web":[33,168],"content":[34,73],"plagued":[36],"by":[37],"the":[38,49,116,141,171],"so-called":[39],"boilerplate:":[40],"ads,":[41],"incomplete":[42],"noisy":[44,119],"text":[45],"and":[46,65,71,84,92,109,131,151,153,166],"rests":[47],"navigation":[50,56],"structure,":[51],"such":[52],"as":[53],"menus":[54],"bars.":[57],"In":[58],"work,":[60],"we":[61,93],"present":[62],"novel":[64],"efficient":[66],"approach":[67,78],"extract":[69],"useful":[70],"well-formed":[72],"from":[74],"web-scraped":[75],"data.":[76],"Our":[77],"takes":[79],"advantage":[80],"Language":[82],"Models":[83],"their":[85],"implicit":[86],"knowledge":[87],"about":[88],"correctly":[89],"formed":[90],"text,":[91],"demonstrate":[94],"here":[95,140],"that":[96,102,128],"perplexity":[97],"valuable":[100],"artefact":[101],"can":[103],"contribute":[104],"terms":[106],"effectiveness":[108],"efficiency.":[110],"As":[111],"matter":[113],"fact,":[115],"removal":[117],"parts":[120],"leads":[121],"lighter":[123],"AI":[124],"search":[126,150],"solutions":[127],"are":[129],"effective":[130],"entail":[132],"important":[133],"reductions":[134],"resources":[136],"spent.":[137],"We":[138,157],"exemplify":[139],"usefulness":[142],"our":[144,174],"method":[145],"with":[146,163],"two":[147],"downstream":[148],"tasks,":[149],"classification,":[152],"cleaning":[155],"task.":[156],"also":[158],"provide":[159],"Python":[161],"package":[162],"pre-trained":[164],"models":[165],"demo":[169],"demonstrating":[170],"capabilities":[172],"approach.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
