{"id":"https://openalex.org/W2004292021","doi":"https://doi.org/10.1145/1363686.1363793","title":"A wrapper generation system for PDF documents","display_name":"A wrapper generation system for PDF documents","publication_year":2008,"publication_date":"2008-03-16","ids":{"openalex":"https://openalex.org/W2004292021","doi":"https://doi.org/10.1145/1363686.1363793","mag":"2004292021"},"language":"en","primary_location":{"id":"doi:10.1145/1363686.1363793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1363686.1363793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM symposium on Applied computing","raw_type":"proceedings-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/A5043055064","display_name":"Bettina Fazzinga","orcid":"https://orcid.org/0000-0001-8611-2377"},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Bettina Fazzinga","raw_affiliation_strings":["DEIS-UNICAL, Rende, Italy","DEIS-UNICAL, Rende-Italy#TAB#"],"affiliations":[{"raw_affiliation_string":"DEIS-UNICAL, Rende, Italy","institution_ids":["https://openalex.org/I45204951"]},{"raw_affiliation_string":"DEIS-UNICAL, Rende-Italy#TAB#","institution_ids":["https://openalex.org/I45204951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002811447","display_name":"Sergio Flesca","orcid":"https://orcid.org/0000-0002-4164-940X"},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sergio Flesca","raw_affiliation_strings":["DEIS-UNICAL, Rende, Italy","DEIS-UNICAL, Rende-Italy#TAB#"],"affiliations":[{"raw_affiliation_string":"DEIS-UNICAL, Rende, Italy","institution_ids":["https://openalex.org/I45204951"]},{"raw_affiliation_string":"DEIS-UNICAL, Rende-Italy#TAB#","institution_ids":["https://openalex.org/I45204951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021211836","display_name":"Andrea Tagarelli","orcid":"https://orcid.org/0000-0002-8142-503X"},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Tagarelli","raw_affiliation_strings":["DEIS-UNICAL, Rende, Italy","DEIS-UNICAL, Rende-Italy#TAB#"],"affiliations":[{"raw_affiliation_string":"DEIS-UNICAL, Rende, Italy","institution_ids":["https://openalex.org/I45204951"]},{"raw_affiliation_string":"DEIS-UNICAL, Rende-Italy#TAB#","institution_ids":["https://openalex.org/I45204951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003115848","display_name":"Salvatore Garruzzo","orcid":null},"institutions":[{"id":"https://openalex.org/I59725666","display_name":"University of Reggio Calabria","ror":"https://ror.org/041sz8d87","country_code":"IT","type":"education","lineage":["https://openalex.org/I59725666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Garruzzo","raw_affiliation_strings":["DIMET-UNIRC, Reggio Calabria, Italy"],"affiliations":[{"raw_affiliation_string":"DIMET-UNIRC, Reggio Calabria, Italy","institution_ids":["https://openalex.org/I59725666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005904043","display_name":"Elio Masciari","orcid":"https://orcid.org/0000-0002-1778-5321"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elio Masciari","raw_affiliation_strings":["ICAR-CNR, Rende, Italy","ICAR-CNR, RENDE, Italy"],"affiliations":[{"raw_affiliation_string":"ICAR-CNR, Rende, Italy","institution_ids":["https://openalex.org/I3005160176"]},{"raw_affiliation_string":"ICAR-CNR, RENDE, Italy","institution_ids":["https://openalex.org/I3005160176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043055064"],"corresponding_institution_ids":["https://openalex.org/I45204951"],"apc_list":null,"apc_paid":null,"fwci":0.846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83112587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8244431614875793},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7150691151618958},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5715610980987549},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5530440211296082},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5469591021537781},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5252482295036316},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5129970908164978},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5023951530456543},{"id":"https://openalex.org/keywords/program-comprehension","display_name":"Program comprehension","score":0.44881290197372437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31349509954452515},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17860695719718933},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.14821061491966248},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09079068899154663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8244431614875793},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7150691151618958},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5715610980987549},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5530440211296082},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5469591021537781},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5252482295036316},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5129970908164978},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5023951530456543},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.44881290197372437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31349509954452515},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17860695719718933},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.14821061491966248},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09079068899154663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1363686.1363793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1363686.1363793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM symposium on Applied computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1480552834","https://openalex.org/W1616576116","https://openalex.org/W1751031993","https://openalex.org/W2005646337","https://openalex.org/W2016627289","https://openalex.org/W2057841333","https://openalex.org/W2104086170","https://openalex.org/W2136500370","https://openalex.org/W2148210463","https://openalex.org/W2162340487","https://openalex.org/W2163915185","https://openalex.org/W2912565176","https://openalex.org/W4211007335"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"The":[0,87],"widespread":[1],"use":[2],"of":[3,18,56,63,80,84,98],"the":[4,15,54,78,81,92],"PDF":[5,35,40,85,100],"format":[6],"for":[7,31,52],"exchanging":[8],"print-oriented":[9],"documents":[10],"raises":[11],"new":[12],"challenges":[13],"in":[14,38,91],"research":[16],"field":[17],"information":[19,33,58],"extraction.":[20],"In":[21],"this":[22],"paper":[23,93],"we":[24,48],"present":[25],"a":[26,39,61,95],"novel":[27],"wrapper":[28],"generation":[29],"system":[30],"extracting":[32],"from":[34],"documents.":[36,86],"Objects":[37],"document":[41],"are":[42],"accessible":[43],"by":[44],"their":[45],"position,":[46],"thus":[47],"exploit":[49],"spatial":[50],"constraints":[51],"driving":[53],"extraction":[55],"relevant":[57],"according":[59],"to":[60],"set":[62],"group":[64],"type":[65],"definitions.":[66],"Moreover,":[67],"using":[68],"fuzzy":[69],"logic":[70],"based":[71],"conditions":[72],"enables":[73],"effectively":[74],"handling":[75],"uncertainty":[76],"on":[77],"comprehension":[79],"layout":[82],"structure":[83],"experimental":[88],"results":[89],"shown":[90],"state":[94],"good":[96],"accuracy":[97],"our":[99],"wrapping":[101],"system.":[102]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
