{"id":"https://openalex.org/W2328679616","doi":"https://doi.org/10.1145/2837185.2837278","title":"Using apps and rules in contextual workflows to semantically extract data from documents","display_name":"Using apps and rules in contextual workflows to semantically extract data from documents","publication_year":2015,"publication_date":"2015-12-11","ids":{"openalex":"https://openalex.org/W2328679616","doi":"https://doi.org/10.1145/2837185.2837278","mag":"2328679616"},"language":"en","primary_location":{"id":"doi:10.1145/2837185.2837278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837185.2837278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"},"type":"conference-paper","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/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ermelinda Oro","raw_affiliation_strings":["National Research Council (CNR), Rende (CS), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council (CNR), Rende (CS), Italy","institution_ids":["https://openalex.org/I4210155236"]}]},{"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/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Ruffolo","raw_affiliation_strings":["National Research Council (CNR), Rende (CS), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council (CNR), Rende (CS), Italy","institution_ids":["https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210155236"],"apc_list":null,"apc_paid":null,"fwci":0.2896,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56124392,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13194","display_name":"ICT in Developing Communities","score":0.9984999895095825,"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/T13194","display_name":"ICT in Developing Communities","score":0.9984999895095825,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8763762712478638},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7213214635848999},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6406837105751038},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5992907285690308},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5767305493354797},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.5319222211837769},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.5036165118217468},{"id":"https://openalex.org/keywords/mantra","display_name":"Mantra","score":0.4898702800273895},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42416226863861084},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.41665083169937134},{"id":"https://openalex.org/keywords/sparql","display_name":"SPARQL","score":0.4163006544113159},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4147849678993225},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3634520471096039},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2748374938964844},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.22234028577804565},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.190496563911438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13679644465446472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8763762712478638},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7213214635848999},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6406837105751038},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5992907285690308},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5767305493354797},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.5319222211837769},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.5036165118217468},{"id":"https://openalex.org/C2778171436","wikidata":"https://www.wikidata.org/wiki/Q131510","display_name":"Mantra","level":2,"score":0.4898702800273895},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42416226863861084},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.41665083169937134},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.4163006544113159},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4147849678993225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3634520471096039},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2748374938964844},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.22234028577804565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.190496563911438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13679644465446472},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1145/2837185.2837278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837185.2837278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1937348540","https://openalex.org/W1964470889","https://openalex.org/W1969082155","https://openalex.org/W2022710553","https://openalex.org/W2046797334","https://openalex.org/W2059727598","https://openalex.org/W2062417941","https://openalex.org/W2075714840","https://openalex.org/W2118928552","https://openalex.org/W2131975293","https://openalex.org/W2159948904","https://openalex.org/W2166500779","https://openalex.org/W2169454125","https://openalex.org/W2169696634","https://openalex.org/W2494940261"],"related_works":["https://openalex.org/W4206764195","https://openalex.org/W2155929612","https://openalex.org/W199330785","https://openalex.org/W2267627180","https://openalex.org/W2402575682","https://openalex.org/W2396236980","https://openalex.org/W2187569332","https://openalex.org/W98016204","https://openalex.org/W602498611","https://openalex.org/W2085965157"],"abstract_inverted_index":{"If":[0],"smartly":[1],"utilized,":[2],"Big":[3,85],"Data":[4,79,86,89],"locked":[5],"in":[6,17,32,41,44,59,68,121],"unstructured":[7,45],"sources,":[8],"such":[9],"as":[10,169,171],"PDF":[11],"documents,":[12,168],"can":[13],"yield":[14],"unprecedented":[15],"insights":[16],"solving":[18],"tough":[19],"business":[20,23],"issues,":[21],"optimizing":[22],"processes":[24],"and":[25,62,117,137,141,144,173],"improving":[26],"customer":[27],"relations.":[28],"The":[29],"challenge":[30],"addressed":[31],"this":[33],"paper":[34],"is":[35,55,158],"to":[36,57,83,115,160],"unlock":[37],"the":[38,76,103,105,155,175],"value":[39],"held":[40],"data":[42,70],"plunged":[43],"document.":[46],"We":[47,74],"describe":[48],"how":[49],"a":[50,60,162],"contextual":[51,93],"workflow":[52],"based":[53],"approach":[54,157],"used":[56],"address,":[58],"semantic":[61,138],"flexible":[63],"way,":[64],"various":[65],"problems":[66],"arising":[67],"processing":[69],"contained":[71,120],"into":[72,87],"documents.":[73],"present":[75],"MANTRA":[77,106,110],"Smart":[78,88],"Platform,":[80],"which":[81],"enables":[82],"turn":[84],"by":[90,96],"means":[91],"of":[92,150,165,177],"workflows":[94],"composed":[95],"smart-cloud":[97],"applications":[98,151],"(APPs":[99],"for":[100],"short).":[101],"Among":[102],"others,":[104],"Language":[107],"APP":[108],"executes":[109],"rules":[111,134],"that":[112,154],"are":[113,152],"able":[114,159],"extract":[116,172],"annotate":[118],"information":[119,176],"heterogeneous":[122,166],"sources":[123],"(raw":[124],"text,":[125],"PDF,":[126],"HTML":[127],"or":[128],"other":[129],"presentation-oriented":[130],"document":[131],"format).":[132],"Such":[133],"exploit":[135],"syntactic":[136],"expressions,":[139],"visual":[140],"spatial":[142],"features,":[143],"natural":[145],"language":[146],"capabilities.":[147],"Real":[148],"cases":[149],"showing":[153],"proposed":[156],"process":[161],"large":[163],"amount":[164],"input":[167],"well":[170],"consolidate":[174],"interest.":[178]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
