{"id":"https://openalex.org/W3102354094","doi":"https://doi.org/10.1145/3366424.3383547","title":"Boilerplate Removal using a Neural Sequence Labeling Model","display_name":"Boilerplate Removal using a Neural Sequence Labeling Model","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3102354094","doi":"https://doi.org/10.1145/3366424.3383547","mag":"3102354094"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366424.3383547","pdf_url":null,"source":{"id":"https://openalex.org/S4306506650","display_name":"Companion Proceedings of the The Web Conference 2018","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.14294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064040097","display_name":"Jurek Leonhardt","orcid":"https://orcid.org/0000-0002-1992-9261"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jurek Leonhardt","raw_affiliation_strings":["L3S Research Center Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075681290","display_name":"Avishek Anand","orcid":"https://orcid.org/0000-0002-0163-0739"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Avishek Anand","raw_affiliation_strings":["L3S Research Center Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027689420","display_name":"Megha Khosla","orcid":"https://orcid.org/0000-0002-0319-3181"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Megha Khosla","raw_affiliation_strings":["L3S Research Center Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":26,"citation_normalized_percentile":{"value":0.958522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"229"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9594,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9502,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boilerplate-text","display_name":"Boilerplate text","score":0.52021784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399369},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.65443826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.52573407},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.52021784},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44685724},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4422074},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4319099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34296602},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.31140518},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.12111789},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.089156926}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366424.3383547","pdf_url":null,"source":{"id":"https://openalex.org/S4306506650","display_name":"Companion Proceedings of the The Web Conference 2018","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2004.14294","pdf_url":"https://arxiv.org/pdf/2004.14294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2004.14294","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2004.14294","pdf_url":"https://arxiv.org/pdf/2004.14294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.57,"display_name":"Quality education"}],"grants":[],"datasets":[],"versions":["https://openalex.org/W3021347373","https://openalex.org/W3102354094"],"referenced_works_count":16,"referenced_works":["https://openalex.org/W116870935","https://openalex.org/W15548","https://openalex.org/W1989338554","https://openalex.org/W2007442002","https://openalex.org/W2012575882","https://openalex.org/W2019264297","https://openalex.org/W2040075907","https://openalex.org/W2051141368","https://openalex.org/W2101909884","https://openalex.org/W2120101509","https://openalex.org/W2140208587","https://openalex.org/W2157316480","https://openalex.org/W2158051716","https://openalex.org/W2201534957","https://openalex.org/W2767272365","https://openalex.org/W2964079897"],"related_works":["https://openalex.org/W2885559332","https://openalex.org/W2626548695","https://openalex.org/W2548348270","https://openalex.org/W2102269195","https://openalex.org/W2074126298","https://openalex.org/W2055154498","https://openalex.org/W2051097555","https://openalex.org/W2017818230","https://openalex.org/W1541158057","https://openalex.org/W1519586109"],"abstract_inverted_index":{"The":[0],"extraction":[1],"of":[2,45,61,118,152],"main":[3],"content":[4,117],"from":[5,16,65],"web":[6,26,62,102,120,153],"pages":[7,121,154],"is":[8,143],"an":[9],"important":[10],"task":[11],"for":[12,22,48],"numerous":[13],"applications,":[14],"ranging":[15],"usability":[17],"aspects,":[18],"like":[19],"reader":[20],"views":[21],"news":[23],"articles":[24],"in":[25,52,72,100,149],"browsers,":[27],"to":[28,57,109,138,145,147],"information":[29],"retrieval":[30],"or":[31],"natural":[32],"language":[33],"processing.":[34],"Existing":[35],"approaches":[36],"are":[37,55],"lacking":[38],"as":[39,104],"they":[40],"rely":[41,85],"on":[42,86],"large":[43],"amounts":[44],"hand-crafted":[46,88],"features":[47,89],"classification.":[49],"This":[50,106],"results":[51],"models":[53],"that":[54,82,98,140],"tailored":[56],"a":[58,66,77,101,111,133],"specific":[59],"distribution":[60],"pages,":[63],"e.g.":[64],"certain":[67],"time":[68],"frame,":[69],"but":[70,90],"lack":[71],"generalization":[73],"power.":[74],"We":[75],"propose":[76],"neural":[78],"sequence":[79],"labeling":[80],"model":[81,142],"does":[83],"not":[84],"any":[87],"takes":[91],"only":[92],"the":[93,116,124,150,157],"HTML":[94],"tags":[95],"and":[96,155],"words":[97],"appear":[99],"page":[103],"input.":[105],"allows":[107],"us":[108],"present":[110],"browser":[112,125],"extension":[113],"which":[114],"highlights":[115],"arbitrary":[119],"directly":[122],"within":[123],"using":[126],"our":[127,141],"model.":[128,159],"In":[129],"addition,":[130],"we":[131],"create":[132],"new,":[134],"more":[135],"current":[136],"dataset":[137],"show":[139],"able":[144],"adapt":[146],"changes":[148],"structure":[151],"outperform":[156],"state-of-the-art":[158]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3102354094","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":3}],"updated_date":"2025-02-20T00:46:49.886405","created_date":"2020-11-23"}