{"id":"https://openalex.org/W2084682994","doi":"https://doi.org/10.1145/1816123.1816137","title":"Using word sense discrimination on historic document collections","display_name":"Using word sense discrimination on historic document collections","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W2084682994","doi":"https://doi.org/10.1145/1816123.1816137","mag":"2084682994"},"language":"en","primary_location":{"id":"doi:10.1145/1816123.1816137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"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/A5003859694","display_name":"Nina Tahmasebi","orcid":"https://orcid.org/0000-0003-1688-1845"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nina Tahmasebi","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060719581","display_name":"Kai Niklas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kai Niklas","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028901491","display_name":"Thomas Theuerkauf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Theuerkauf","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070155789","display_name":"Thomas Risse","orcid":"https://orcid.org/0000-0001-6248-1709"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Risse","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003859694"],"corresponding_institution_ids":["https://openalex.org/I4210136150"],"apc_list":null,"apc_paid":null,"fwci":45.2397,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.99636965,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9868000149726868,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.8287643194198608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956099510192871},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.7322254776954651},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.65762859582901},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.623771071434021},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5659852623939514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5529699921607971},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5179232954978943},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.4687153398990631},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.4457997679710388},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2782108187675476},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.12343186140060425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06487497687339783}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8287643194198608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956099510192871},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7322254776954651},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.65762859582901},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.623771071434021},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5659852623939514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529699921607971},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5179232954978943},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.4687153398990631},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.4457997679710388},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2782108187675476},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.12343186140060425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06487497687339783},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1816123.1816137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.417.8932","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.417.8932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://liwa-project.eu/images/publications/temp_file_UsingWordSenseDiscriminationOnHistoricDocumentCollections.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.417.9064","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.417.9064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://liwa-project.eu/images/publications/jcdl2010-tahmasebi4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1497130516","https://openalex.org/W1530933250","https://openalex.org/W1546317785","https://openalex.org/W1602659612","https://openalex.org/W1974533997","https://openalex.org/W2000951787","https://openalex.org/W2050712820","https://openalex.org/W2068737686","https://openalex.org/W2081580037","https://openalex.org/W2092124750","https://openalex.org/W2112090702","https://openalex.org/W2116671632","https://openalex.org/W2117805756","https://openalex.org/W2128838341","https://openalex.org/W2130337399","https://openalex.org/W2166776180","https://openalex.org/W2264308890","https://openalex.org/W2997914541","https://openalex.org/W6632726884","https://openalex.org/W6693034680"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W2188275805","https://openalex.org/W2904069821","https://openalex.org/W3087778885","https://openalex.org/W2401522294","https://openalex.org/W1962828410","https://openalex.org/W2253780618","https://openalex.org/W4205429340","https://openalex.org/W4232239836","https://openalex.org/W2079838398"],"abstract_inverted_index":{"Word":[0],"sense":[1,47,98,148],"discrimination":[2,48,77,99,149],"is":[3,123],"the":[4,21,71,76,84,110,127,130,141],"first,":[5],"important":[6,32],"step":[7,78,138],"towards":[8],"automatic":[9],"detection":[10,85],"of":[11,40,70,86,119,129,143,164],"language":[12,55,87],"evolution":[13],"within":[14],"large,":[15],"historic":[16,106,121],"document":[17],"collections.":[18],"By":[19],"comparing":[20],"found":[22,74],"word":[23,46,72,97,115,147],"senses":[24,73],"over":[25],"time,":[26],"we":[27,94,139],"can":[28,100],"reveal":[29],"and":[30,38,58,108],"use":[31],"information":[33],"that":[34,96,109],"will":[35],"improve":[36],"understanding":[37],"accessibility":[39,118],"a":[41,80,91,136,162],"digital":[42],"archive.":[43],"Algorithms":[44],"for":[45],"have":[49,59],"been":[50,61],"developed":[51],"while":[52],"keeping":[53],"today\u2019s":[54],"in":[56,75,153],"mind":[57],"thus":[60],"evaluated":[62],"on":[63,83,146,158],"well":[64],"selected,":[65],"modern":[66],"datasets.":[67],"The":[68,159],"quality":[69,128],"has":[79],"large":[81],"impact":[82],"evolution.":[88],"Therefore,":[89],"as":[90,135],"first":[92],"step,":[93],"verify":[95],"successfully":[101],"be":[102],"applied":[103],"to":[104,114],"digitized":[105,120],"documents":[107],"results":[111],"correctly":[112],"correspond":[113],"senses.":[116],"Because":[117],"collections":[122],"influenced":[124],"also":[125],"by":[126],"optical":[131],"character":[132],"recognition":[133],"(OCR),":[134],"second":[137],"investigate":[140],"effects":[142],"OCR":[144],"errors":[145],"results.":[150],"All":[151],"evaluations":[152],"this":[154],"paper":[155],"are":[156],"performed":[157],"Times":[160],"Archive,":[161],"collection":[163],"newspaper":[165],"articles":[166]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
