{"id":"https://openalex.org/W2967327409","doi":"https://doi.org/10.1109/jcdl.2019.00014","title":"Corpus Assembly as Text Data Integration from Digital Libraries and the Web","display_name":"Corpus Assembly as Text Data Integration from Digital Libraries and the Web","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2967327409","doi":"https://doi.org/10.1109/jcdl.2019.00014","mag":"2967327409"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2019.00014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5044841280","display_name":"Udo Hahn","orcid":"https://orcid.org/0000-0002-5052-0245"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Udo Hahn","raw_affiliation_strings":["Jena University Language & Information Engineering, Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering, Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044560062","display_name":"Tinghui Duan","orcid":"https://orcid.org/0000-0002-3324-0938"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tinghui Duan","raw_affiliation_strings":["Graduate School \"Romanticism as a Model\", Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Graduate School \"Romanticism as a Model\", Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.137,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.243908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":69,"max":74},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"28"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9977,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9904,"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/digitization","display_name":"Digitization","score":0.7228068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77013725},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7228068},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.65720916},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6162696},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.61137086},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.56956625},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5229457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46815705},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.43423986},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16918609},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08700448},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2019.00014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.79}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":10,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1976978913","https://openalex.org/W1995693596","https://openalex.org/W2295941310","https://openalex.org/W2507419453","https://openalex.org/W2513477448","https://openalex.org/W2575782020","https://openalex.org/W2577651287","https://openalex.org/W2740804691","https://openalex.org/W2807055569"],"related_works":["https://openalex.org/W4308177873","https://openalex.org/W4254109238","https://openalex.org/W4251369848","https://openalex.org/W3202479762","https://openalex.org/W3167700301","https://openalex.org/W2746392713","https://openalex.org/W2480493049","https://openalex.org/W2399890175","https://openalex.org/W2163748916","https://openalex.org/W1539704186"],"abstract_inverted_index":{"We":[0],"here":[1],"explore":[2],"a":[3,35,75,83,151,174],"new":[4],"corpus":[5,73,161],"construction":[6],"workflow":[7],"which":[8,109],"exploits":[9],"the":[10,14,22,42,52,79,87,97,115,121,157],"inherent":[11],"potential":[12],"of":[13,17,38,46,78,89,114,128,162],"growing":[15],"number":[16],"Digital":[18,90],"Libraries":[19],"worldwide":[20],"and":[21,65,130,154],"ever-expanding":[23],"Internet":[24],"Archive.":[25],"Rather":[26],"than":[27],"building":[28],"corpora":[29],"from":[30,68,105,120],"scratch":[31],"(which":[32],"typically":[33],"consumes":[34],"huge":[36],"amount":[37],"resources),":[39],"we":[40,92,139],"search":[41],"Web":[43,137],"for":[44,96,176],"fragments":[45,132],"relevant":[47],"digitized":[48],"contents":[49],"scattered":[50,134],"across":[51],"world,":[53],"check":[54],"their":[55],"digitization":[56],"quality,":[57,64],"select":[58],"those":[59,69],"digital":[60],"versions":[61],"with":[62,74],"highest":[63],"finally":[66],"assemble":[67,142],"pieces":[70,148],"an":[71],"integrated":[72],"maximum":[76],"coverage":[77],"targeted":[80],"resource.":[81],"As":[82],"use":[84],"case":[85],"within":[86],"framework":[88],"Humanities,":[91],"illustrate":[93],"this":[94],"approach":[95],"Allgemeine":[98],"Literatur-Zeitung":[99],"(General":[100],"Literature":[101],"Gazette,":[102],"ALZ)":[103],"published":[104],"1785":[106],"to":[107,141,145,170],"1849,":[108],"is":[110],"considered":[111],"as":[112,173],"one":[113],"most":[116],"important":[117],"text":[118],"collections":[119],"Romantic":[122],"Age":[123],"in":[124],"Germany.":[125],"With":[126],"lots":[127],"incomplete":[129],"overlapping":[131],"physically":[133],"over":[135],"many":[136],"sites,":[138],"started":[140],"these":[143,147],"fragments,":[144],"bind":[146],"together":[149],"using":[150],"homogeneous":[152],"format,":[153],"thus":[155],"constructed":[156],"first":[158],"(almost)":[159],"complete":[160],"ALZ,":[163],"now":[164],"accessible":[165],"(in":[166],"XML":[167],"format":[168],"obeying":[169],"TEI":[171],"standards)":[172],"whole":[175],"in-depth":[177],"scientific":[178],"investigations.":[179]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2967327409","counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2024-12-13T05:54:01.977399","created_date":"2019-08-22"}