{"id":"https://openalex.org/W7100723388","doi":null,"title":"A survey of semi-automatic extraction and transformation. http://www-db.stanford.edu/ crespo/publications","display_name":"A survey of semi-automatic extraction and transformation. http://www-db.stanford.edu/ crespo/publications","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7100723388"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.6408","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.6408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.stanford.edu/~crespo/publications/extract.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5103504775","display_name":"Arturo Crespo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arturo Crespo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141559254","display_name":"Jan Jannink","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Jannink","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Erich Neuhold","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erich Neuhold","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110197580","display_name":"Michael Rys","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Rys","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039385406","display_name":"Rudi Studer A","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rudi Studer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9667999744415283,"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 Mining and Analysis","score":0.9667999744415283,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.012299999594688416,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.004000000189989805,"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/semi-automatic-extraction","display_name":"semi-automatic extraction","score":0.6949999928474426},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.7139999866485596},{"id":"https://openalex.org/keywords/document-conversion","display_name":"document conversion","score":0.7839999794960022},{"id":"https://openalex.org/keywords/document-structure-extraction","display_name":"document structure extraction","score":0.6480000019073486},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.8659999966621399},{"id":"https://openalex.org/keywords/document-processing","display_name":"document processing","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002999782562256},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.43779999017715454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3109000027179718}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.6408","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.6408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.stanford.edu/~crespo/publications/extract.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7096423500","https://openalex.org/W7098989995","https://openalex.org/W7097642930","https://openalex.org/W4251901041","https://openalex.org/W7097121005","https://openalex.org/W120184336","https://openalex.org/W7099722476","https://openalex.org/W164114955","https://openalex.org/W7034656722","https://openalex.org/W4296765674"],"abstract_inverted_index":{"Abstract":[0],"|":[1],"This":[2,35],"paper":[3,36,80],"studies":[4],"the":[5,17,25,49,55,70,76,97,108],"extraction":[6,77],"and":[7,23,42,47,73,96,101],"transformation":[8],"problem":[9,14],"on":[10,61,85],"documents.":[11],"Solving":[12],"this":[13],"entails":[15],"extracting":[16,45],"structures":[18,26],"contained":[19],"in":[20,107],"a":[21,62,83,89],"document":[22],"transforming":[24,48],"to":[27],"make":[28],"them":[29],"available":[30,71],"for":[31,44],"further":[32],"automatic":[33],"processing.":[34],"provides":[37],"an":[38],"overview":[39,58],"of":[40,69,75,91],"methods":[41],"tools":[43,92],"information":[46,51],"extracted":[50],"as":[52],"required":[53],"by":[54],"end-user.":[56],"The":[57,79],"is":[59],"based":[60],"taxonomy":[63],"that":[64,99],"classi":[65],"es":[66],"both":[67],"characteristics":[68],"sources":[72],"properties":[74],"techniques.":[78],"concludes":[81],"with":[82,93],"perspective":[84],"future":[86],"developments,":[87],"including":[88],"discussion":[90],"learning":[94],"capabilities":[95],"role":[98],"XML":[100],"other":[102],"related":[103],"standards":[104],"will":[105],"play":[106],"future.":[109],"1.":[110]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-27T00:00:00"}