{"id":"https://openalex.org/W2907705782","doi":"https://doi.org/10.13053/cys-22-4-3062","title":"A New Proposal for Evaluating Web Page Cleaning Tools","display_name":"A New Proposal for Evaluating Web Page Cleaning Tools","publication_year":2018,"publication_date":"2018-12-31","ids":{"openalex":"https://openalex.org/W2907705782","doi":"https://doi.org/10.13053/cys-22-4-3062","mag":"2907705782"},"language":"es","primary_location":{"id":"doi:10.13053/cys-22-4-3062","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-22-4-3062","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-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/A5070835832","display_name":"Ga\u00ebl Lejeune","orcid":"https://orcid.org/0000-0002-4795-2362"},"institutions":[{"id":"https://openalex.org/I4210114212","display_name":"Laboratoire de Linguistique Formelle","ror":"https://ror.org/0223bz716","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210114212","https://openalex.org/I4210150854"]},{"id":"https://openalex.org/I4389425349","display_name":"Sens, Texte, Informatique, Histoire","ror":"https://ror.org/02q5emw59","country_code":null,"type":"facility","lineage":["https://openalex.org/I39804081","https://openalex.org/I4389425349"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ga\u00ebl Lejeune","raw_affiliation_strings":["STIH-LC - \u00c9quipe Linguistique computationnelle (France)","STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)"],"affiliations":[{"raw_affiliation_string":"STIH-LC - \u00c9quipe Linguistique computationnelle (France)","institution_ids":["https://openalex.org/I4210114212","https://openalex.org/I4389425349"]},{"raw_affiliation_string":"STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","institution_ids":["https://openalex.org/I4389425349","https://openalex.org/I4389425349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016191521","display_name":"Lichao Zhu","orcid":"https://orcid.org/0000-0003-4432-0236"},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lichao Zhu","raw_affiliation_strings":["Pl\u00e9iade - Centre de recherche pluridisciplinaire en Lettres, Langues, Sciences Humaines et des Soci\u00e9t\u00e9s (UFR LSHS - Universit\u00e9 Paris 13\r\n99, av. Jean-Baptiste Cl\u00e9ment\r\n93430  Villetaneuse - France)"],"affiliations":[{"raw_affiliation_string":"Pl\u00e9iade - Centre de recherche pluridisciplinaire en Lettres, Langues, Sciences Humaines et des Soci\u00e9t\u00e9s (UFR LSHS - Universit\u00e9 Paris 13\r\n99, av. Jean-Baptiste Cl\u00e9ment\r\n93430  Villetaneuse - France)","institution_ids":["https://openalex.org/I4210091279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070835832"],"corresponding_institution_ids":["https://openalex.org/I4210114212","https://openalex.org/I4389425349"],"apc_list":null,"apc_paid":null,"fwci":2.4636,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92186879,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"22","issue":"4","first_page":null,"last_page":null},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9889000058174133,"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":0.7936121821403503},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7823052406311035},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7433725595474243},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5250349044799805},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.47168949246406555},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.446354478597641},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4307847023010254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40127554535865784},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3243781328201294},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08147820830345154},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06236827373504639},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.059374332427978516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936121821403503},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7823052406311035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7433725595474243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5250349044799805},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47168949246406555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.446354478597641},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4307847023010254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40127554535865784},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3243781328201294},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08147820830345154},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06236827373504639},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.059374332427978516},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.13053/cys-22-4-3062","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-22-4-3062","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02467732v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02467732","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computaci\u00f3n y sistemas, 2018, &#x27E8;10.13053/CyS-22-4-3062&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W32751375","https://openalex.org/W2020254000","https://openalex.org/W2048525542","https://openalex.org/W2120101509","https://openalex.org/W2126372189","https://openalex.org/W2140208587","https://openalex.org/W2154484245","https://openalex.org/W2188533213","https://openalex.org/W2578576916","https://openalex.org/W2593361376","https://openalex.org/W2907705782","https://openalex.org/W2916815186","https://openalex.org/W3154772965"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W1975289146","https://openalex.org/W4234772502","https://openalex.org/W2105887828","https://openalex.org/W2122599759","https://openalex.org/W2380685755","https://openalex.org/W4236520801","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W3135843367"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,35],"tackle":[4],"the":[5,20,28,62,67,70,74,84,87,100,105,111,125,132,136],"problem":[6],"of":[7,9,31,39,69,76,113],"evaluation":[8,45,60,94,138],"Web":[10],"Content":[11],"Extraction":[12],"tools.":[13],"This":[14],"task":[15,126],"is":[16,47,128],"seldom":[17],"studied":[18,106],"in":[19,50,83,104],"literature":[21],"although":[22],"it":[23],"has":[24],"important":[25],"consequences":[26],"on":[27,61,73],"linguistic":[29],"processing":[30],"web-based":[32],"corpora.":[33],"Here,":[34],"compare":[36],"two":[37],"types":[38],"evaluation.":[40],"Firstly,":[41],"an":[42,57,77],"intrinsic":[43,85,137],"(content-based)":[44],"which":[46],"carried":[48],"out":[49],"a":[51,114],"multilingual":[52],"setting":[53],"(five":[54],"languages).":[55],"Secondly,":[56],"extrinsic":[58,93],"(task-based)":[59],"same":[63],"corpus":[64],"by":[65],"studying":[66],"effects":[68],"cleaning":[71,117],"step":[72],"performances":[75,133],"NLP":[78],"pipeline.":[79],"We":[80,96,108],"show":[81,98],"that":[82,99,110,127],"evaluation,":[86],"results":[88,101],"are":[89],"not":[90],"consistent":[91],"with":[92,122],"results.":[95],"also":[97],"differ":[102],"greatly":[103],"languages.":[107],"conclude":[109],"choice":[112],"web":[115],"page":[116],"tool":[118],"should":[119],"be":[120],"made":[121],"respect":[123],"to":[124],"tackled":[129],"rather":[130],"than":[131],"observed":[134],"through":[135],"scheme.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
