{"id":"https://openalex.org/W1982870905","doi":"https://doi.org/10.1145/2539150.2539228","title":"Metadata Extraction from Books with Facts about Austria","display_name":"Metadata Extraction from Books with Facts about Austria","publication_year":2013,"publication_date":"2013-12-02","ids":{"openalex":"https://openalex.org/W1982870905","doi":"https://doi.org/10.1145/2539150.2539228","mag":"1982870905"},"language":"en","primary_location":{"id":"doi:10.1145/2539150.2539228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2539150.2539228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of International Conference on Information Integration and Web-based Applications &amp; Services","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/A5052958478","display_name":"Petra Korica-Pehserl","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Petra Korica-Pehserl","raw_affiliation_strings":["Institute for Information Systems and Computer Media, Inffeldgasse 16c, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute for Information Systems and Computer Media, Inffeldgasse 16c, 8010 Graz, Austria","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026864542","display_name":"Hermann Maurer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Maurer","raw_affiliation_strings":["Institute for Information Systems and Computer Media, Inffeldgasse 16c, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute for Information Systems and Computer Media, Inffeldgasse 16c, 8010 Graz, Austria","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052958478"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06045445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9825000166893005,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9782999753952026,"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/metadata","display_name":"Metadata","score":0.9139426946640015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8545221090316772},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7476913332939148},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5938825607299805},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4662301540374756},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4490611255168915},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.43411827087402344},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.41078537702560425}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9139426946640015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8545221090316772},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7476913332939148},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5938825607299805},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4662301540374756},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4490611255168915},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.43411827087402344},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.41078537702560425},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2539150.2539228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2539150.2539228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W18748505","https://openalex.org/W169035307","https://openalex.org/W182623531","https://openalex.org/W202361227","https://openalex.org/W642670006","https://openalex.org/W1520377376","https://openalex.org/W2049781914","https://openalex.org/W2096765155","https://openalex.org/W2111620957","https://openalex.org/W2119174796","https://openalex.org/W2132655161","https://openalex.org/W2159709895","https://openalex.org/W2162590473","https://openalex.org/W4285719527","https://openalex.org/W6607409905","https://openalex.org/W6683883671"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056"],"abstract_inverted_index":{"Digitized":[0],"fact":[1,135],"books":[2,89,114,136],"are":[3,84,109],"valuable":[4],"sources":[5],"of":[6,53,64,103],"knowledge.":[7,17],"Full-text":[8],"search":[9,47],"is":[10],"a":[11,120],"powerful":[12],"tool":[13],"to":[14,33,46,58,92],"access":[15],"such":[16],"However,":[18],"it":[19,79],"often":[20,90],"delivers":[21],"too":[22],"many":[23],"results":[24],"for":[25,41,48],"general":[26],"queries.":[27],"Therefore":[28],"we":[29,98,127,131],"propose":[30],"an":[31],"approach":[32,130],"find":[34],"relevant":[35,40],"data":[36,66],"by":[37],"extracting":[38],"metadata":[39,55],"each":[42],"page":[43],"and":[44,112,139],"allow":[45],"pages":[49],"on":[50,133],"the":[51,62,129],"basis":[52],"their":[54],"as":[56],"alternative":[57],"full-text":[59],"search.":[60],"Given":[61],"size":[63],"scanned":[65],"(high":[67],"quality":[68],"image":[69],"scans)":[70],"clearly":[71],"this":[72,125,144],"extraction":[73],"cannot":[74],"be":[75,93],"done":[76],"manually.":[77],"As":[78],"turns":[80],"out,":[81],"although":[82],"there":[83],"some":[85],"common":[86],"aspects,":[87],"different":[88,134],"need":[91],"treated":[94],"differently.":[95],"In":[96,124],"particular":[97],"can":[99],"distinguish":[100],"two":[101],"kinds":[102],"books:":[104],"lexicons":[105],"(dictionaries)":[106],"where":[107],"items":[108],"arranged":[110],"alphabetically":[111],"other":[113],"that":[115],"describe":[116,128],"various":[117],"topics":[118],"in":[119,137],"more":[121],"narrative":[122],"style.":[123],"paper":[126],"used":[132],"detail":[138],"share":[140],"our":[141],"learnings":[142],"from":[143],"subject.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
