{"id":"https://openalex.org/W2165512325","doi":"https://doi.org/10.1142/s0218213012500327","title":"FIRST-ORDER LOGIC RULE INDUCTION FOR INFORMATION EXTRACTION IN WEB RESOURCES","display_name":"FIRST-ORDER LOGIC RULE INDUCTION FOR INFORMATION EXTRACTION IN WEB RESOURCES","publication_year":2012,"publication_date":"2012-08-17","ids":{"openalex":"https://openalex.org/W2165512325","doi":"https://doi.org/10.1142/s0218213012500327","mag":"2165512325"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213012500327","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5061484787","display_name":"Jos\u00e9 Ignacio Fern\u00e1ndez-Villamor","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"JOS\u00c9 IGNACIO FERN\u00c1NDEZ-VILLAMOR","raw_affiliation_strings":["Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, Universidad Polit\u00e9cnica de Madrid, Avenida Complutense, 30 Madrid, 28040, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, Universidad Polit\u00e9cnica de Madrid, Avenida Complutense, 30 Madrid, 28040, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023155010","display_name":"Carlos \u00c1. Iglesias","orcid":"https://orcid.org/0000-0002-1755-2712"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"CARLOS \u00c1NGEL IGLESIAS","raw_affiliation_strings":["Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, Universidad Polit\u00e9cnica de Madrid, Avenida Complutense, 30 Madrid, 28040, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, Universidad Polit\u00e9cnica de Madrid, Avenida Complutense, 30 Madrid, 28040, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020614200","display_name":"Mercedes Ruiz Garijo","orcid":"https://orcid.org/0000-0002-7910-9767"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"MERCEDES GARIJO","raw_affiliation_strings":["Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, Universidad Polit\u00e9cnica de Madrid, Avenida Complutense, 30 Madrid, 28040, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda de Sistemas Telem\u00e1ticos, Universidad Polit\u00e9cnica de Madrid, Avenida Complutense, 30 Madrid, 28040, Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.945,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.966942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":"21","issue":"06","first_page":"1250032","last_page":"1250032"},"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":0.9769,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9594,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness","score":0.6364045},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.609031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89821947},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6826334},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6364045},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.609031},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.580829},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5439073},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5373264},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.514073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4480918},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41031802},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3435686},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2750814},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10045183},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213012500327","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W138259698","https://openalex.org/W1553019137","https://openalex.org/W1566513354","https://openalex.org/W1577231857","https://openalex.org/W1971518650","https://openalex.org/W1978478796","https://openalex.org/W1989993068","https://openalex.org/W2001959118","https://openalex.org/W2015191210","https://openalex.org/W2033072307","https://openalex.org/W2046545050","https://openalex.org/W2053998130","https://openalex.org/W2085533860","https://openalex.org/W2115770258","https://openalex.org/W2119662395","https://openalex.org/W2125055259","https://openalex.org/W2134150392","https://openalex.org/W2135479443","https://openalex.org/W2138405339","https://openalex.org/W2149074433","https://openalex.org/W2150721933","https://openalex.org/W2163780445","https://openalex.org/W2172102660","https://openalex.org/W2180101051","https://openalex.org/W2265991260","https://openalex.org/W2408277762","https://openalex.org/W4239696231","https://openalex.org/W4285719527","https://openalex.org/W6578894","https://openalex.org/W99921237"],"related_works":["https://openalex.org/W4385731361","https://openalex.org/W4302086745","https://openalex.org/W36911888","https://openalex.org/W2626998250","https://openalex.org/W2557094866","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W2004087619","https://openalex.org/W1656419755","https://openalex.org/W1539890081"],"abstract_inverted_index":{"Information":[0],"extraction":[1],"out":[2],"of":[3,26,34,37,96,124,143],"web":[4,49,79,126],"pages,":[5,127],"commonly":[6],"known":[7],"as":[8,89],"screen":[9],"scraping,":[10],"is":[11,20,39,44,62],"usually":[12],"performed":[13],"through":[14],"wrapper":[15,43],"induction,":[16],"a":[17,41,64,104,122],"technique":[18],"that":[19,40,66,71],"based":[21,84],"on":[22,85,103,113,121],"the":[23,31,48,137,140,144],"internal":[24,106],"structure":[25],"HTML":[27],"documents.":[28],"As":[29],"such,":[30],"main":[32],"limitation":[33],"these":[35],"kinds":[36],"techniques":[38],"generated":[42],"only":[45],"useful":[46],"for":[47],"page":[50],"it":[51,61],"was":[52],"designed":[53],"for.":[54],"To":[55],"overcome":[56],"this,":[57],"in":[58],"this":[59],"paper":[60],"proposed":[63],"system":[65,117],"generates":[67],"first-order":[68],"logic":[69],"rules":[70,82],"can":[72],"be":[73],"used":[74],"to":[75,111],"extract":[76],"data":[77],"from":[78],"pages.":[80],"These":[81],"are":[83,109],"visual":[86],"features":[87],"such":[88],"font":[90],"size,":[91],"elements":[92],"positioning":[93],"or":[94],"types":[95],"contents.":[97],"Thus,":[98],"they":[99],"do":[100],"not":[101],"depend":[102],"document's":[105],"structure,":[107],"and":[108,132,139],"able":[110],"work":[112],"different":[114,125],"sites.":[115],"The":[116],"has":[118],"been":[119],"validated":[120],"set":[123],"showing":[128],"very":[129],"high":[130],"precision":[131],"good":[133],"recall,":[134],"which":[135],"validates":[136],"robustness":[138],"generalization":[141],"capabilities":[142],"approach.":[145]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2165512325","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2024-12-11T04:37:06.849959","created_date":"2016-06-24"}