{"id":"https://openalex.org/W2046352419","doi":"https://doi.org/10.1145/2815833.2815838","title":"A Comparison of Different Strategies for Automated Semantic Document Annotation","display_name":"A Comparison of Different Strategies for Automated Semantic Document Annotation","publication_year":2015,"publication_date":"2015-09-29","ids":{"openalex":"https://openalex.org/W2046352419","doi":"https://doi.org/10.1145/2815833.2815838","mag":"2046352419"},"language":"en","primary_location":{"id":"doi:10.1145/2815833.2815838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2815833.2815838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Knowledge Capture","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049945587","display_name":"Gregor Gro\u00dfe-B\u00f6lting","orcid":"https://orcid.org/0000-0003-0303-1796"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gregor Gro\u00dfe-B\u00f6lting","raw_affiliation_strings":["Kiel University, Kiel, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kiel University, Kiel, Germany","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089069811","display_name":"Chifumi Nishioka","orcid":"https://orcid.org/0000-0002-1853-3038"},"institutions":[{"id":"https://openalex.org/I2800024560","display_name":"ZBW \u2013 Leibniz-Informationszentrum Wirtschaft","ror":"https://ror.org/03a96gc12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800024560","https://openalex.org/I315704651"]},{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chifumi Nishioka","raw_affiliation_strings":["ZBW -- Leibniz Information Centre for Economics, Kiel, Germany, Kiel University, Kiel, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZBW -- Leibniz Information Centre for Economics, Kiel, Germany, Kiel University, Kiel, Germany","institution_ids":["https://openalex.org/I2800024560","https://openalex.org/I32021983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005533034","display_name":"Ansgar Scherp","orcid":"https://orcid.org/0000-0002-2653-9245"},"institutions":[{"id":"https://openalex.org/I2800024560","display_name":"ZBW \u2013 Leibniz-Informationszentrum Wirtschaft","ror":"https://ror.org/03a96gc12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800024560","https://openalex.org/I315704651"]},{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ansgar Scherp","raw_affiliation_strings":["ZBW -- Leibniz Information Centre for Economics, Kiel, Germany, Kiel University, Kiel, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZBW -- Leibniz Information Centre for Economics, Kiel, Germany, Kiel University, Kiel, Germany","institution_ids":["https://openalex.org/I2800024560","https://openalex.org/I32021983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8372165560722351},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6347827911376953},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5785753726959229},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4844410717487335},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44133487343788147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.365813285112381},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09087198972702026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372165560722351},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6347827911376953},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5785753726959229},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4844410717487335},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44133487343788147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365813285112381},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09087198972702026}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2815833.2815838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2815833.2815838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Knowledge Capture","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.stir.ac.uk:1893/28054","is_oa":false,"landing_page_url":"http://dspace.stir.ac.uk/bitstream/1893/28054/1/Grosse-Bolting-etal-CP.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400268","display_name":"Stirling Online Research Repository (University of Stirling)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12093191","host_organization_name":"University of Stirling","host_organization_lineage":["https://openalex.org/I12093191"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:pub.zbw.eu:11108/221","is_oa":false,"landing_page_url":"http://hdl.handle.net/11108/221","pdf_url":null,"source":{"id":"https://openalex.org/S4306402552","display_name":"ZBW Publication Archive (ZBW \u2013 Leibniz Information Centre for Economics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800024560","host_organization_name":"ZBW \u2013 Leibniz-Informationszentrum Wirtschaft","host_organization_lineage":["https://openalex.org/I2800024560"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W133296","https://openalex.org/W109131495","https://openalex.org/W1462843577","https://openalex.org/W1506806321","https://openalex.org/W1525595230","https://openalex.org/W1534665184","https://openalex.org/W1596451018","https://openalex.org/W1638133288","https://openalex.org/W1663973292","https://openalex.org/W1854214752","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W2001082470","https://openalex.org/W2028738615","https://openalex.org/W2030903088","https://openalex.org/W2048679005","https://openalex.org/W2060772621","https://openalex.org/W2068903979","https://openalex.org/W2072644219","https://openalex.org/W2102126527","https://openalex.org/W2107473756","https://openalex.org/W2115024484","https://openalex.org/W2126326126","https://openalex.org/W2133286915","https://openalex.org/W2138621811","https://openalex.org/W2152143870","https://openalex.org/W2341381586","https://openalex.org/W6639055396","https://openalex.org/W7015831105"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W2181757899"],"abstract_inverted_index":{"We":[0,94,124],"introduce":[1],"a":[2,60,193],"framework":[3,25],"for":[4],"automated":[5],"semantic":[6,47],"document":[7],"annotation":[8,20,33],"that":[9,115],"is":[10,26,159],"composed":[11],"of":[12,62,103,137,172],"four":[13],"processes,":[14],"namely":[15],"concept":[16,18,40,56],"extraction,":[17,41],"activation,":[19,57],"selection,":[21],"and":[22,30,53,65,112,145,147,152,161],"evaluation.":[23],"The":[24,177],"used":[27],"to":[28,192],"implement":[29],"compare":[31,59,72],"different":[32,83,101],"strategies":[34,84,98],"motivated":[35],"by":[36,133,181],"the":[37,97,126,150,156,165,169,180],"literature.":[38],"For":[39,55,68,149,164],"we":[42,58,71,80],"apply":[43],"entity":[44,138],"detection":[45,139],"with":[46,92,140],"hierarchical":[48],"knowledge":[49],"bases,":[50],"Tri-gram,":[51],"RAKE,":[52],"LDA.":[54],"set":[61],"statistical,":[63],"hierarchy-based,":[64],"graph-based":[66,90,141],"methods.":[67],"selecting":[69],"annotations,":[70],"top-k":[73],"as":[74,76],"well":[75],"kNN.":[77,93,148],"In":[78],"total,":[79],"define":[81],"43":[82],"including":[85],"novel":[86,135],"combinations":[87],"like":[88],"using":[89,99],"activation":[91,142],"have":[95],"evaluated":[96],"three":[100,107,131],"datasets":[102,132],"varying":[104],"size":[105],"from":[106],"scientific":[108],"disciplines":[109],"(economics,":[110],"politics,":[111],"computer":[113,166],"science)":[114],"contain":[116],"100,":[117],"000":[118],"manually":[119],"labeled":[120],"documents":[121,196],"in":[122],"total.":[123],"obtain":[125],"best":[127,157],"results":[128],"on":[129,184],"all":[130],"our":[134],"combination":[136],"(e.g.,":[143],"HITS":[144],"Degree)":[146],"economic":[151],"political":[153],"science":[154,167],"datasets,":[155],"F-measure":[158,171],".39":[160],".28,":[162],"respectively.":[163],"dataset,":[168],"maximum":[170],".33":[173],"can":[174],"be":[175],"reached.":[176],"experiments":[178],"are":[179,190],"far":[182],"largest":[183],"scholarly":[185],"content":[186],"annotation,":[187],"which":[188],"typically":[189],"up":[191],"few":[194],"hundred":[195],"per":[197],"dataset":[198],"only.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}