{"id":"https://openalex.org/W2064706480","doi":"https://doi.org/10.1145/2767109.2767112","title":"FOREST","display_name":"FOREST","publication_year":2015,"publication_date":"2015-05-31","ids":{"openalex":"https://openalex.org/W2064706480","doi":"https://doi.org/10.1145/2767109.2767112","mag":"2064706480"},"language":"en","primary_location":{"id":"doi:10.1145/2767109.2767112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2767109.2767112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Workshop on Web and Databases","raw_type":"proceedings-article"},"type":"preprint","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/A5013772837","display_name":"Marilena Oita","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marilena Oita","raw_affiliation_strings":["T\u00e9l\u00e9com ParisTech; CNRS LTCI &amp; CustomerMatrix, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com ParisTech; CNRS LTCI &amp; CustomerMatrix, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035414136","display_name":"Pierre Senellart","orcid":"https://orcid.org/0000-0002-7909-5369"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Senellart","raw_affiliation_strings":["T\u00e9l\u00e9com ParisTech; CNRS LTCI &amp; NUS; CNRS IPAL Paris, France &amp; Singapore","CNRS LTCI & NUS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com ParisTech; CNRS LTCI &amp; NUS; CNRS IPAL Paris, France &amp; Singapore","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"CNRS LTCI & NUS","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09243374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":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/T13976","display_name":"Web visibility and informetrics","score":0.9749000072479248,"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9438999891281128,"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/computer-science","display_name":"Computer science","score":0.8428671956062317},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.694951593875885},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6281504034996033},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5950357913970947},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49466535449028015},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.46935707330703735},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4661952555179596},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.445304811000824},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4264596700668335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14360517263412476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428671956062317},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.694951593875885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6281504034996033},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5950357913970947},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49466535449028015},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.46935707330703735},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4661952555179596},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.445304811000824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4264596700668335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14360517263412476},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2767109.2767112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2767109.2767112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Workshop on Web and Databases","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W133582","https://openalex.org/W134247304","https://openalex.org/W426968574","https://openalex.org/W1553019137","https://openalex.org/W1583739829","https://openalex.org/W1803802947","https://openalex.org/W1973828215","https://openalex.org/W1974725911","https://openalex.org/W1999120268","https://openalex.org/W2015551056","https://openalex.org/W2019577381","https://openalex.org/W2037600449","https://openalex.org/W2040075907","https://openalex.org/W2049365470","https://openalex.org/W2058201162","https://openalex.org/W2064716575","https://openalex.org/W2072489225","https://openalex.org/W2104086170","https://openalex.org/W2104972336","https://openalex.org/W2115221525","https://openalex.org/W2119088569","https://openalex.org/W2120101509","https://openalex.org/W2128836931","https://openalex.org/W2129595335","https://openalex.org/W2132916655","https://openalex.org/W2133814403","https://openalex.org/W2140208587","https://openalex.org/W2150721933","https://openalex.org/W2151265933","https://openalex.org/W2154652894","https://openalex.org/W2167859982","https://openalex.org/W2169347997","https://openalex.org/W2171364811","https://openalex.org/W2182452677","https://openalex.org/W2183235533","https://openalex.org/W2293993557","https://openalex.org/W2319012534","https://openalex.org/W2611186022","https://openalex.org/W6633154970","https://openalex.org/W6682631176","https://openalex.org/W6700017563"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4237510188","https://openalex.org/W36911888","https://openalex.org/W2083329789","https://openalex.org/W2376574812","https://openalex.org/W4385731361"],"abstract_inverted_index":{"Content-intensive":[0],"websites,":[1],"e.g.,":[2],"of":[3,22,45],"blogs":[4],"or":[5,34],"news,":[6],"present":[7,37],"pages":[8],"that":[9],"contain":[10],"Web":[11,46,50,69,75],"articles":[12,47],"automatically":[13],"generated":[14,66],"by":[15,67],"content":[16,25,65,97],"management":[17],"systems.":[18],"Identification":[19],"and":[20,58,71,86,88],"extraction":[21,44],"their":[23],"main":[24,64],"is":[26],"critical":[27],"in":[28,73,96],"many":[29],"applications,":[30],"such":[31],"as":[32],"indexing":[33],"classification.":[35],"We":[36,77],"a":[38,68],"novel":[39],"unsupervised":[40],"approach":[41],"for":[42],"the":[43,63],"from":[48],"dynamically-generated":[49],"pages.":[51,76],"Our":[52],"system,":[53],"called":[54],"Forest,":[55],"combines":[56],"structural":[57],"information-based":[59],"features":[60],"to":[61,83],"target":[62],"source,":[70],"published":[72],"associated":[74],"extensively":[78],"evaluate":[79],"Forest":[80],"with":[81],"respect":[82],"various":[84],"baselines":[85],"datasets,":[87],"report":[89],"improved":[90],"results":[91],"over":[92],"state-of-the":[93],"art":[94],"techniques":[95],"extraction.":[98]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
