{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:15:15Z","timestamp":1729613715590,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/jcdl.2017.7991565","type":"proceedings-article","created":{"date-parts":[[2017,7,27]],"date-time":"2017-07-27T16:40:17Z","timestamp":1501173617000},"page":"1-10","source":"Crossref","is-referenced-by-count":3,"title":["A Text Extraction Software Benchmark Based on a Synthesized Dataset"],"prefix":"10.1109","author":[{"given":"Kresimir","family":"Duretec","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Rauber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Becker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"579","author":"wing","year":"2000","journal-title":"Respectful type converters"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1002\/stvr.456","author":"utting","year":"2012","journal-title":"A taxonomy of model-based testing approaches Software Testing Verification and Reliability 22"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-54906-9_9"},{"key":"ref30","first-page":"1275","author":"strecker","year":"2009","journal-title":"Automated Ground Truth Data Generation for Newspaper Document Images In 2009 10th InternationalConference on Document Analysis and Recognition"},{"key":"ref10","first-page":"16","author":"fetherston","year":"2012","journal-title":"Towards the Development of a Test Corpus of Digital Objects for the Evaluation of File Format Identification Tools and Signatures International Journal of Digital Curation 7 1 (March 2012)"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2s","DOI":"10.1016\/j.diin.2009.06.016","article-title":"Bringing science to digitalforensics with standardized forensic corpora","author":"garfinkel","year":"2009","journal-title":"Digital Investigation"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1065385.1065418"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2005.12.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12823-8_1"},{"key":"ref15","first-page":"91","author":"lease","year":"2013","journal-title":"Crowdsourcing for information retrieval iIntroduction to the special issue Information Retrieval 16 2"},{"key":"ref16","article-title":"Binary Codes Capable of Correcting Deletions, Insertions and Reversals","author":"levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1255175.1255193"},{"journal-title":"2010 Digital Object Characterization Document Conversion and Qualiity Assurance In Dagstuhl Seminar Proceedings Schloss Dagstuhl-Leibniz-Zentrum fur Informatik","year":"0","author":"natasa","key":"ref18"},{"key":"ref19","first-page":"540","author":"di","year":"0","journal-title":"Model based test validation and oracles for data acquisition systems In 2013 IEEE\/ACM 28th InternationalConference on Automated Software Engineering (ASE)"},{"key":"ref28","first-page":"120","author":"ross","year":"2013","journal-title":"Generation of a Skeleton Corpus of Digital Objects for the Validation and Evaluation of Format Identification Tools and Signatures International Eournal of Digital Curation"},{"key":"ref4","first-page":"349","author":"becker","year":"0","journal-title":"Free Benchmark Corpora for Preservation Experiments Using Model-driven Engineering to Generate Data Sets In Proceedings of the 13th ACM\/IEEE-CS Joint Conference on Digital Libraries (ECDL ‘13)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2003.1201189"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1109\/TSE.2014.2372785","author":"barr","year":"2015","journal-title":"The Oracle Problem in Software Testing A Survey IEEE Transactions on Software Engineering"},{"key":"ref6","volume":"2","author":"becker","year":"2016","journal-title":"The Benchmarking Forum at IPRES 2015 D-Lib Magazine"},{"key":"ref29","first-page":"391","article-title":"Programs, Tests, and Oracles: The Foundations of Testing Revisited","author":"matt","year":"0","journal-title":"Proceedings of the 33rd International Conference on Software Engineering (ICSE)"},{"key":"ref5","first-page":"1","volume":"7","author":"becker","year":"2017","journal-title":"The Challenge of Test Data Quality in Data Processing J Data and Information Quality 8 2"},{"journal-title":"BenchmarkDP - Text extraction from general documents benchmark dataset","year":"2017","author":"duretec","key":"ref8"},{"journal-title":"Benchmarks for Digital Preservation tools In Proceedings of the 12th InternationalConference on Digital Preservation (IPRES)","year":"0","author":"duretec","key":"ref7"},{"key":"ref2","first-page":"1978","author":"saswat","year":"2013","journal-title":"An orchestrated survey of methodologies for automated software test case generation Journal of Systems and Software 86 8"},{"journal-title":"Proposal for an Evaluation Framework for Compliance Checkers for Long-term Digital Preservation In 12th Italian ResearchConf on Digital Libraries (IRCDL)","year":"2016","author":"nicola","key":"ref9"},{"journal-title":"Methods for Evaluating Text Extraction Toolkits An Exploratory Investigation Technical Report DTIC Document","year":"2015","author":"allison","key":"ref1"},{"key":"ref20","first-page":"1","author":"di nardo","year":"0","journal-title":"Generating Complex and Faulty Test Data through Model-Based Mutation Analysis In 2015 IEEE 8th InternationalConference on Software Testing Verification and Validation (ICST)"},{"journal-title":"On the Need for Benchmark Corpora in DigitalPreservation In 2nd DELOS Conference on Digital Libraries","year":"2007","author":"neumayer","key":"ref22"},{"journal-title":"National Digital Stewardship Alliance 2014 2015 National Agenda for Digital Stewardship Technical Report","year":"0","key":"ref21"},{"key":"ref24","first-page":"971","author":"pasternack","year":"0","journal-title":"2009 Extracting Article Text from the Web with Maximum Subsequence Segmentation In Proceedings of the 18th International Conference on World Wide Web (WWW ‘09)"},{"journal-title":"Discipline-Independent Text Information Extraction from Heterogeneous Styled References Using Knowledge from the Web Ph D Disertation Virginia Polytechnic Institute and State University","year":"2013","author":"park","key":"ref23"},{"key":"ref26","first-page":"359","volume":"1","author":"sellers","year":"1980","journal-title":"The theory and computation of evolutionary distances pattern recognition E ournal of algorithms"},{"journal-title":"Layout-aware text extraction from full-text PDF of scientificarticles Source Code for Biology and Medicine 7 1","year":"2012","author":"ramakrishnan","key":"ref25"}],"event":{"name":"2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL)","start":{"date-parts":[[2017,6,19]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2017,6,23]]}},"container-title":["2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7988694\/7990621\/07991565.pdf?arnumber=7991565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T14:28:25Z","timestamp":1569940105000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7991565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/jcdl.2017.7991565","relation":{},"subject":[],"published":{"date-parts":[[2017,6]]}}}