{"id":"https://openalex.org/W1594534918","doi":"https://doi.org/10.1007/978-3-540-88873-4_38","title":"Towards a System for Ontology-Based Information Extraction from PDF Documents","display_name":"Towards a System for Ontology-Based Information Extraction from PDF Documents","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W1594534918","doi":"https://doi.org/10.1007/978-3-540-88873-4_38","mag":"1594534918"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-88873-4_38","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"book-chapter","type_crossref":"book-chapter","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/A5038972694","display_name":"Ermelinda Oro","orcid":"https://orcid.org/0000-0002-5529-1007"},"institutions":[{"id":"https://openalex.org/I4210103492","display_name":"Advanced Computer System (Italy)","ror":"https://ror.org/018mrwd51","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210103492"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ermelinda Oro","raw_affiliation_strings":["Department of Computer Science and System Science (DEIS), Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and System Science (DEIS), Italy","institution_ids":["https://openalex.org/I4210103492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045708216","display_name":"Massimo Ruffolo","orcid":"https://orcid.org/0000-0002-4094-4810"},"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"]},{"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":"Massimo Ruffolo","raw_affiliation_strings":["Institute of High Performance Computing and Networking of CNR (ICAR-CNR), University of Calabria, 87036, Rende (CS), Italy"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing and Networking of CNR (ICAR-CNR), University of Calabria, 87036, Rende (CS), Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I45204951"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"apc_paid":null,"fwci":0.344,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.569133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":70,"max":74},"biblio":{"volume":null,"issue":null,"first_page":"1482","last_page":"1499"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Extraction and Crawling Techniques","score":0.9999,"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 Extraction and Crawling Techniques","score":0.9999,"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/T10679","display_name":"QoS-Aware Web Services Composition and Semantic Matching","score":0.9864,"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/T10215","display_name":"Semantic Web and Ontology Development","score":0.9836,"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/ontology","display_name":"Ontology","score":0.586236},{"id":"https://openalex.org/keywords/web-data-extraction","display_name":"Web Data Extraction","score":0.57926},{"id":"https://openalex.org/keywords/knowledge-representation","display_name":"Knowledge Representation","score":0.565973},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information Retrieval","score":0.525437},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42925647},{"id":"https://openalex.org/keywords/ontology-learning","display_name":"Ontology learning","score":0.41399765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9004181},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.8156487},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.65072393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.56537676},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5098197},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.47824043},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.449749},{"id":"https://openalex.org/C137003198","wikidata":"https://www.wikidata.org/wiki/Q7247296","display_name":"Process ontology","level":3,"score":0.4463618},{"id":"https://openalex.org/C22550185","wikidata":"https://www.wikidata.org/wiki/Q7095047","display_name":"Ontology-based data integration","level":3,"score":0.43817046},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42925647},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.414061},{"id":"https://openalex.org/C2777002027","wikidata":"https://www.wikidata.org/wiki/Q3620938","display_name":"Ontology learning","level":5,"score":0.41399765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30602127},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.30394906},{"id":"https://openalex.org/C50971890","wikidata":"https://www.wikidata.org/wiki/Q7635093","display_name":"Suggested Upper Merged Ontology","level":4,"score":0.27518526},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-88873-4_38","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"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":44,"referenced_works":["https://openalex.org/W1480552834","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1499578805","https://openalex.org/W1558832481","https://openalex.org/W1559525484","https://openalex.org/W1584713052","https://openalex.org/W1591167068","https://openalex.org/W1723485573","https://openalex.org/W180206698","https://openalex.org/W1943691658","https://openalex.org/W1964071625","https://openalex.org/W1986394669","https://openalex.org/W1990117407","https://openalex.org/W2002089154","https://openalex.org/W2003250112","https://openalex.org/W2005646337","https://openalex.org/W2052409393","https://openalex.org/W2064466058","https://openalex.org/W2065555531","https://openalex.org/W2067416210","https://openalex.org/W2084130127","https://openalex.org/W2092772700","https://openalex.org/W2103931177","https://openalex.org/W2111353076","https://openalex.org/W2115294179","https://openalex.org/W2115461474","https://openalex.org/W2126260950","https://openalex.org/W2134150392","https://openalex.org/W2140587192","https://openalex.org/W2140785769","https://openalex.org/W2148210463","https://openalex.org/W2155879015","https://openalex.org/W2341078838","https://openalex.org/W2478892373","https://openalex.org/W2489428738","https://openalex.org/W2573956962","https://openalex.org/W2798573942","https://openalex.org/W3217008510","https://openalex.org/W4206031975","https://openalex.org/W4253103663","https://openalex.org/W4285719527","https://openalex.org/W573586472","https://openalex.org/W62735629"],"related_works":["https://openalex.org/W4255991504","https://openalex.org/W3009694037","https://openalex.org/W2384218079","https://openalex.org/W2375862234","https://openalex.org/W2156556194","https://openalex.org/W2075489301","https://openalex.org/W2051508632","https://openalex.org/W2039166384","https://openalex.org/W2024342824","https://openalex.org/W147727067"],"abstract_inverted_index":{"Ontologies":[0],"enable":[1,137],"to":[2,130,139],"directly":[3],"encode":[4],"domain":[5],"knowledge":[6,78,99],"in":[7,100],"software":[8],"applications,":[9],"so":[10],"ontology-based":[11,66],"systems":[12],"can":[13],"exploit":[14],"the":[15,27,44,123,150,152,155,165,169],"meaning":[16],"of":[17,26,33,46,102,122,154,164,168,176],"information":[18,36,48,67,114],"for":[19,70],"providing":[20],"advanced":[21],"and":[22,30,59,96,106,162],"intelligent":[23],"functionalities.":[24],"One":[25],"most":[28],"interesting":[29],"promising":[31],"application":[32],"ontologies":[34,132],"is":[35,126,158],"extraction":[37,45,68,107],"from":[38,49,145],"unstructured":[39,146],"documents.":[40,148],"In":[41,149],"this":[42],"area":[43],"meaningful":[47],"PDF":[50,71,147],"documents":[51,72],"has":[52],"been":[53],"recently":[54],"recognized":[55],"as":[56],"an":[57,65],"important":[58],"challenging":[60],"problem.":[61],"This":[62],"paper":[63,151],"proposes":[64],"system":[69,171],"founded":[73],"on":[74],"a":[75,177],"well":[76],"suited":[77],"representation":[79],"approach":[80,87,125,157],"named":[81],"self-populating":[82],"ontology":[83,103],"(SPO).":[84],"The":[85,119],"SPO":[86,124,156,170],"combines":[88],"object-oriented":[89],"logic-based":[90],"features":[91,161],"with":[92,142],"formal":[93],"grammar":[94],"capabilities":[95],"allows":[97,129],"expressing":[98],"term":[101],"schemas,":[104],"instances,":[105],"rules":[108,135],"(called":[109],"descriptors)":[110],"aimed":[111],"at":[112],"extracting":[113],"having":[115],"also":[116],"tabular":[117],"form.":[118],"novel":[120],"aspect":[121],"that":[127,136],"it":[128],"represent":[131],"enriched":[133],"by":[134,174],"them":[138],"populate":[140],"them-self":[141],"instances":[143],"extracted":[144],"tractability":[153],"proven.":[159],"Moreover,":[160],"behavior":[163],"prototypical":[166],"implementation":[167],"are":[172],"illustrated":[173],"means":[175],"running":[178],"example.":[179]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1594534918","counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2024-11-18T21:31:50.649563","created_date":"2016-06-24"}
