{"id":"https://openalex.org/W4412377994","doi":"https://doi.org/10.1145/3726302.3730234","title":"Multilingual Evaluation of Main Content Extractors for Web Pages","display_name":"Multilingual Evaluation of Main Content Extractors for Web Pages","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377994","doi":"https://doi.org/10.1145/3726302.3730234"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730234","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730234","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730234","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118969397","display_name":"Aur\u00e9lien Bournonville","orcid":null},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Aur\u00e9lien Bournonville","raw_affiliation_strings":["University of Caen Normandy, Caen, France and Babbar.tech, Petit-Quevilly, France"],"affiliations":[{"raw_affiliation_string":"University of Caen Normandy, Caen, France and Babbar.tech, Petit-Quevilly, France","institution_ids":["https://openalex.org/I98702875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043440123","display_name":"Ga\u00ebl Dias","orcid":"https://orcid.org/0000-0002-5840-1603"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Dias","raw_affiliation_strings":["University of Caen Normandy, Caen, France"],"affiliations":[{"raw_affiliation_string":"University of Caen Normandy, Caen, France","institution_ids":["https://openalex.org/I98702875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033861896","display_name":"Thomas Largillier","orcid":null},"institutions":[{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Largillier","raw_affiliation_strings":["Babbar.tech, Petit-Quevilly, France"],"affiliations":[{"raw_affiliation_string":"Babbar.tech, Petit-Quevilly, France","institution_ids":["https://openalex.org/I190752583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022180230","display_name":"Emmanuel Marchand","orcid":null},"institutions":[{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Marchand","raw_affiliation_strings":["Babbar.tech, Petit-Quevilly, France"],"affiliations":[{"raw_affiliation_string":"Babbar.tech, Petit-Quevilly, France","institution_ids":["https://openalex.org/I190752583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070355272","display_name":"Fabrice Maurel","orcid":"https://orcid.org/0000-0002-8644-2461"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabrice Maurel","raw_affiliation_strings":["University of Caen Normandy, Caen, France"],"affiliations":[{"raw_affiliation_string":"University of Caen Normandy, Caen, France","institution_ids":["https://openalex.org/I98702875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099872181","display_name":"Guillaume Pitel","orcid":"https://orcid.org/0000-0001-6172-4342"},"institutions":[{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Pitel","raw_affiliation_strings":["Babbar.tech, Petit-Quevilly, France"],"affiliations":[{"raw_affiliation_string":"Babbar.tech, Petit-Quevilly, France","institution_ids":["https://openalex.org/I190752583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008711104","display_name":"Fran\u00e7ois Rioult","orcid":"https://orcid.org/0000-0001-8162-0997"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Rioult","raw_affiliation_strings":["University of Caen Normandy, Caen, France"],"affiliations":[{"raw_affiliation_string":"University of Caen Normandy, Caen, France","institution_ids":["https://openalex.org/I98702875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5118969397"],"corresponding_institution_ids":["https://openalex.org/I98702875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24776275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2853","last_page":"2857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9835000038146973,"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":0.9819999933242798,"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":0.7899332046508789},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5674498081207275},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5134059190750122},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5034286379814148},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49258214235305786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10779088735580444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899332046508789},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5674498081207275},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5134059190750122},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5034286379814148},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49258214235305786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10779088735580444},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730234","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730234","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05040908v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05040908","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","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":"https://sigir2025.dei.unipd.it/","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730234","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730234","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377994.pdf","grobid_xml":"https://content.openalex.org/works/W4412377994.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1663984431","https://openalex.org/W2036887984","https://openalex.org/W2120101509","https://openalex.org/W2151967815","https://openalex.org/W2154652894","https://openalex.org/W3021347373","https://openalex.org/W3102354094","https://openalex.org/W3177057043","https://openalex.org/W4214671568","https://openalex.org/W4384639986","https://openalex.org/W6682631176"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W42013907"],"abstract_inverted_index":{"Tools":[0],"designed":[1],"to":[2,71,75],"extract":[3],"main":[4],"content":[5],"from":[6],"web":[7],"pages":[8],"require":[9],"thorough":[10],"evaluation,":[11],"yet":[12],"existing":[13],"benchmarks":[14,48],"disproportionately":[15],"focus":[16],"on":[17,96],"English-language":[18],"datasets.":[19],"Consequently,":[20],"previous":[21],"studies":[22],"have":[23],"shown":[24],"that":[25,81],"while":[26,82],"these":[27],"extractors":[28,84],"are":[29],"well-optimized":[30],"for":[31],"English,":[32,64],"their":[33],"effectiveness":[34],"partially":[35],"or":[36,98],"entirely":[37],"diminishes":[38],"in":[39,92],"other":[40],"languages.":[41],"This":[42],"study":[43],"reproduces":[44],"and":[45,67,94],"extends":[46],"recent":[47],"by":[49],"incorporating":[50],"multilingual":[51],"datasets":[52],"as":[53],"a":[54],"key":[55],"factor.":[56],"We":[57],"analyze":[58],"extractor":[59],"performance":[60],"across":[61],"five":[62],"languages-Greek,":[63],"Polish,":[65],"Russian,":[66],"Chinese-highlighting":[68],"the":[69],"need":[70],"adapt":[72],"extraction":[73],"models":[74],"linguistic":[76],"variations.":[77],"Our":[78],"results":[79],"show":[80],"some":[83],"maintain":[85],"stable":[86],"performance,":[87],"others":[88],"suffer":[89],"significant":[90],"drops":[91],"precision":[93],"recall":[95],"non-English":[97],"structurally":[99],"irregular":[100],"pages.":[101]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
