{"id":"https://openalex.org/W3007849886","doi":"https://doi.org/10.1109/bigdata47090.2019.9005587","title":"Probabilistic Named Entity Recognition for nonstandard format entities using cooccurrence word embeddings","display_name":"Probabilistic Named Entity Recognition for nonstandard format entities using cooccurrence word embeddings","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007849886","doi":"https://doi.org/10.1109/bigdata47090.2019.9005587","mag":"3007849886"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9005587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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/A5016121540","display_name":"Jabir Alshehabi Al-Ani","orcid":"https://orcid.org/0000-0002-0553-2538"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jabir Alshehabi AlAni","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021136553","display_name":"Maria Fasli","orcid":"https://orcid.org/0000-0001-8831-102X"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maria Fasli","raw_affiliation_strings":["Institute for Analytics and Data Science, School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Institute for Analytics and Data Science, School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016121540"],"corresponding_institution_ids":["https://openalex.org/I110002522"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19836411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"2077","last_page":"2086"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9955999851226807,"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":0.8340843319892883},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7952448725700378},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7120617032051086},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6896429061889648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6521518230438232},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5863149166107178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5732899904251099},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5405269265174866},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5342074632644653},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4823148250579834},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22696378827095032},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09590500593185425},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08613482117652893},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.0860440731048584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340843319892883},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7952448725700378},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7120617032051086},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6896429061889648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6521518230438232},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5863149166107178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5732899904251099},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5405269265174866},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5342074632644653},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4823148250579834},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22696378827095032},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09590500593185425},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08613482117652893},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0860440731048584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9005587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:ray.yorksj.ac.uk:7562","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/9005587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400356","display_name":"Research at York St John (York St John University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124246371","host_organization_name":"York St John University","host_organization_lineage":["https://openalex.org/I124246371"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7368362902","display_name":null,"funder_award_id":"ES/S007156/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G8322284704","display_name":null,"funder_award_id":"ES/L011859/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1521125545","https://openalex.org/W1533946607","https://openalex.org/W1571096757","https://openalex.org/W1969486090","https://openalex.org/W1989750313","https://openalex.org/W2020278455","https://openalex.org/W2047477415","https://openalex.org/W2070808142","https://openalex.org/W2123442489","https://openalex.org/W2135451108","https://openalex.org/W2143933463","https://openalex.org/W2153848201","https://openalex.org/W2728847680","https://openalex.org/W2911658750","https://openalex.org/W6631217535","https://openalex.org/W6633939012","https://openalex.org/W6682707525","https://openalex.org/W6740332364"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2520117834","https://openalex.org/W626980589","https://openalex.org/W4313162113","https://openalex.org/W1884363728","https://openalex.org/W3133906981"],"abstract_inverted_index":{"The":[0,88,115,132],"use":[1],"of":[2,59,111,120],"short":[3,86],"text":[4],"has":[5,135],"become":[6],"widespread":[7],"in":[8,49,62,80,128,142],"social":[9,18],"media":[10,19],"like":[11],"Twitter":[12],"and":[13,34,39,147],"Facebook.":[14],"Typically,":[15],"users":[16],"on":[17,122],"platforms":[20],"adopt":[21],"nonstandard":[22],"format":[23,84],"terms":[24],"when":[25,126],"posting.":[26],"This":[27],"introduces":[28],"challenges":[29,61],"for":[30],"Information":[31],"Retrieval":[32],"(IR)":[33],"Natural":[35],"Language":[36],"Processing":[37],"(NLP)":[38],"standard":[40,124,140],"or":[41],"classical":[42],"methods":[43,125,141],"tend":[44],"not":[45],"to":[46,144],"perform":[47],"well":[48],"this":[50,53],"domain.":[51],"In":[52],"paper,":[54],"we":[55],"have":[56,103],"addressed":[57],"one":[58],"the":[60,107,139,151],"IR":[63],"which":[64,76],"is":[65],"Named":[66,90],"Entity":[67,91],"Recognition":[68,92],"(NER).":[69],"We":[70],"introduce":[71],"a":[72],"novel":[73],"probabilistic":[74],"approach":[75],"targets":[77],"entities":[78,97],"occurring":[79],"an":[81,118],"informal":[82],"(nonstandard)":[83],"within":[85],"text.":[87],"Probabilistic":[89],"(PNER)":[93],"model":[94],"identifies":[95],"these":[96],"using":[98,106,138],"cooccurrence":[99,109],"patterns.":[100],"These":[101],"patterns":[102],"been":[104,136],"detected":[105],"word":[108],"embeddings":[110],"278.6":[112],"million":[113],"tweets.":[114],"results":[116],"show":[117],"enhancement":[119],"7%":[121],"two":[123],"used":[127],"combination":[129],"with":[130],"PNER.":[131],"testing":[133],"dataset":[134],"created":[137],"addition":[143],"street":[145],"names":[146],"places":[148],"taken":[149],"from":[150],"Open":[152],"Street":[153],"Map":[154],"(OSM)":[155],"database.":[156]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-03-06T00:00:00"}
