{"id":"https://openalex.org/W37065025","doi":"https://doi.org/10.1007/978-3-642-40501-3_15","title":"An Unsupervised Machine Learning Approach to Body Text and Table of Contents Extraction from Digital Scientific Articles","display_name":"An Unsupervised Machine Learning Approach to Body Text and Table of Contents Extraction from Digital Scientific Articles","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W37065025","doi":"https://doi.org/10.1007/978-3-642-40501-3_15","mag":"37065025"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-40501-3_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-40501-3_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5027426964","display_name":"Stefan Klampfl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Stefan Klampfl","raw_affiliation_strings":["Know-Center GmbH, Austria"],"affiliations":[{"raw_affiliation_string":"Know-Center GmbH, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014398832","display_name":"Roman Kern","orcid":"https://orcid.org/0000-0003-0202-6100"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Roman Kern","raw_affiliation_strings":["Know-Center GmbH, Austria","Knowledge Technologies Institute, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Know-Center GmbH, Austria","institution_ids":["https://openalex.org/I4210088621"]},{"raw_affiliation_string":"Knowledge Technologies Institute, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027426964"],"corresponding_institution_ids":["https://openalex.org/I4210088621"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":4.401,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94952539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8704993724822998},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6698939800262451},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6561385989189148},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6293104290962219},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5453330278396606},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5346041917800903},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.5322202444076538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5050778985023499},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48771676421165466},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.48188430070877075},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.44266825914382935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36378175020217896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28002017736434937},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.224319189786911},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14156055450439453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8704993724822998},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6698939800262451},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6561385989189148},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6293104290962219},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5453330278396606},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5346041917800903},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.5322202444076538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5050778985023499},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48771676421165466},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.48188430070877075},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.44266825914382935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36378175020217896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28002017736434937},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.224319189786911},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14156055450439453},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-40501-3_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-40501-3_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.367.8784","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.367.8784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://know-center.tugraz.at/wp-content/uploads/2013/07/tpdl-2013-2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1534730506","https://openalex.org/W1559499673","https://openalex.org/W1972467623","https://openalex.org/W1976373002","https://openalex.org/W1984130280","https://openalex.org/W2009752265","https://openalex.org/W2064354603","https://openalex.org/W2079525773","https://openalex.org/W2110907671","https://openalex.org/W2132313828","https://openalex.org/W2133713322","https://openalex.org/W2150652226","https://openalex.org/W2166633748","https://openalex.org/W2171114275","https://openalex.org/W3023264106"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
