{"id":"https://openalex.org/W130452239","doi":null,"title":"Augmenting Wikipedia with Named Entity Tags.","display_name":"Augmenting Wikipedia with Named Entity Tags.","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W130452239","mag":"130452239"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.128.2450","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.2450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/silviu/papers/ijcnlp08.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/A5080902916","display_name":"Wisam Dakka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wisam Dakka","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040422637","display_name":"Silviu Cucerzan","orcid":"https://orcid.org/0009-0005-0773-0924","observed_orcids":["https://orcid.org/0009-0005-0773-0924"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Silviu Cucerzan","raw_affiliation_strings":["Microsoft"],"raw_orcid":"https://orcid.org/0009-0005-0773-0924","affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.7192,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98184844,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9502000212669373,"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/T10028","display_name":"Topic Modeling","score":0.9502000212669373,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.033399999141693115,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.004399999976158142,"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/wikipedia","display_name":"Wikipedia","score":0.7829999923706055},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.8650000095367432},{"id":"https://openalex.org/keywords/wikipedia-categories","display_name":"Wikipedia categories","score":0.5180000066757202},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6179999709129333},{"id":"https://openalex.org/keywords/web-services","display_name":"web services","score":0.5199999809265137},{"id":"https://openalex.org/keywords/entity-mentions","display_name":"entity mentions","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8725031018257141},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6862324476242065},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6535742282867432},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.6117899417877197},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5785925984382629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5732447504997253},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5679380297660828},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5587380528450012},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5581442713737488},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.41136834025382996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3613993227481842},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.1777043640613556},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.128.2450","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.2450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/silviu/papers/ijcnlp08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.3706","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.3706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/I/I08/I08-1071.pdf","raw_type":"text"},{"id":"mag:130452239","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/I08-1071.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420006","display_name":"International Joint Conference on Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W33304361","https://openalex.org/W86887328","https://openalex.org/W89989934","https://openalex.org/W1482260847","https://openalex.org/W1493526108","https://openalex.org/W1512098439","https://openalex.org/W1548663377","https://openalex.org/W1568620938","https://openalex.org/W1574862351","https://openalex.org/W1592212241","https://openalex.org/W1670263352","https://openalex.org/W1912123407","https://openalex.org/W1995249715","https://openalex.org/W2005422315","https://openalex.org/W2022166150","https://openalex.org/W2029433174","https://openalex.org/W2037603696","https://openalex.org/W2040241219","https://openalex.org/W2047260110","https://openalex.org/W2048679005","https://openalex.org/W2050559027","https://openalex.org/W2056451646","https://openalex.org/W2068882115","https://openalex.org/W2100335205","https://openalex.org/W2118020653","https://openalex.org/W2125055259","https://openalex.org/W2144578941","https://openalex.org/W2149684865","https://openalex.org/W2151846280","https://openalex.org/W2156909104","https://openalex.org/W2170602716","https://openalex.org/W2170654002","https://openalex.org/W2915429162"],"related_works":["https://openalex.org/W7096035978","https://openalex.org/W2104503750","https://openalex.org/W2171609524","https://openalex.org/W2145231152","https://openalex.org/W2252061787","https://openalex.org/W2250783611","https://openalex.org/W7100786022","https://openalex.org/W2186134096","https://openalex.org/W2183985940","https://openalex.org/W2348089566"],"abstract_inverted_index":{"Wikipedia":[0,28,61,70,117],"is":[1],"the":[2,8,24,52,66,69,102,124],"largest":[3],"organized":[4],"knowledge":[5],"repository":[6],"on":[7],"Web,":[9],"increasingly":[10],"employed":[11,80],"by":[12,40],"natural":[13],"language":[14,47],"processing":[15,48],"and":[16,46,63,92],"search":[17],"tools.":[18,49],"In":[19],"this":[20,109],"paper,":[21],"we":[22,54],"investigate":[23],"task":[25],"of":[26,43,60,101,108],"labeling":[27],"pages":[29,62],"with":[30],"standard":[31],"named":[32],"entity":[33,93],"tags,":[34],"which":[35],"can":[36],"be":[37],"used":[38],"further":[39],"a":[41,57,74,106,111],"range":[42],"information":[44,72],"extraction":[45],"To":[50],"train":[51],"classifiers,":[53],"manually":[55],"annotated":[56],"small":[58],"set":[59],"then":[64],"extrapolated":[65],"annotations":[67],"using":[68],"category":[71],"to":[73,123],"much":[75],"larger":[76],"training":[77],"set.":[78],"We":[79,95],"several":[81,100],"distinct":[82],"features":[83],"for":[84,99],"each":[85],"page:":[86],"bag-of-words,":[87],"page":[88,118],"structure,":[89],"abstract,":[90],"titles,":[91],"mentions.":[94],"report":[96],"high":[97],"accuracies":[98],"classifiers":[103],"built.":[104],"As":[105],"result":[107],"work,":[110],"Web":[112],"service":[113],"that":[114],"classifies":[115],"any":[116],"has":[119],"been":[120],"made":[121],"available":[122],"academic":[125],"community.":[126],"1":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
