{"id":"https://openalex.org/W2888160543","doi":"https://doi.org/10.18653/v1/d18-1135","title":"Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set","display_name":"Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888160543","doi":"https://doi.org/10.18653/v1/d18-1135","mag":"2888160543"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1135","pdf_url":"https://www.aclweb.org/anthology/D18-1135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1135.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081017623","display_name":"Radu Tudor Ionescu","orcid":"https://orcid.org/0000-0002-9301-1950"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]},{"id":"https://openalex.org/I4210116052","display_name":"Inception Institute of Artificial Intelligence","ror":"https://ror.org/02664zk40","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210116052"]}],"countries":["AE","RO"],"is_corresponding":false,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":["Inception Institute of Artificial Intelligence (IIAI) Al Maryah Island, Abu Dhabi, UAE","University of Bucharest, Department of Computer Science 14 Academiei, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inception Institute of Artificial Intelligence (IIAI) Al Maryah Island, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210116052"]},{"raw_affiliation_string":"University of Bucharest, Department of Computer Science 14 Academiei, Bucharest, Romania","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030278465","display_name":"Andrei M. Butnaru","orcid":"https://orcid.org/0000-0003-3031-3203"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Andrei M. Butnaru","raw_affiliation_strings":["University of Bucharest, Department of Computer Science 14 Academiei, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bucharest, Department of Computer Science 14 Academiei, Bucharest, Romania","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3582,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8629704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1084","last_page":"1090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9987000226974487,"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":0.9983000159263611,"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/identification","display_name":"Identification (biology)","score":0.7533385753631592},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6879810094833374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875535249710083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6872268915176392},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6821005344390869},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6389155387878418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5582289099693298},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5184911489486694},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.46884217858314514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3282414972782135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32606184482574463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20705121755599976},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11202582716941833},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.04740151762962341}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7533385753631592},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6879810094833374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875535249710083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6872268915176392},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6821005344390869},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6389155387878418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5582289099693298},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5184911489486694},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.46884217858314514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3282414972782135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32606184482574463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20705121755599976},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11202582716941833},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.04740151762962341},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1135","pdf_url":"https://www.aclweb.org/anthology/D18-1135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1135","pdf_url":"https://www.aclweb.org/anthology/D18-1135.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888160543.pdf","grobid_xml":"https://content.openalex.org/works/W2888160543.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W430348815","https://openalex.org/W1510073064","https://openalex.org/W2082439473","https://openalex.org/W2095579012","https://openalex.org/W2107425660","https://openalex.org/W2112483442","https://openalex.org/W2118045473","https://openalex.org/W2125446229","https://openalex.org/W2153353890","https://openalex.org/W2163302275","https://openalex.org/W2163568299","https://openalex.org/W2167277498","https://openalex.org/W2250876960","https://openalex.org/W2401457948","https://openalex.org/W2402118036","https://openalex.org/W2440817164","https://openalex.org/W2465735268","https://openalex.org/W2605323333","https://openalex.org/W2620806258","https://openalex.org/W2740300618","https://openalex.org/W2741287244","https://openalex.org/W2741798456","https://openalex.org/W2752272929","https://openalex.org/W2785748711","https://openalex.org/W2799821893","https://openalex.org/W2963275094","https://openalex.org/W2963486098","https://openalex.org/W2963830885","https://openalex.org/W2963842834","https://openalex.org/W2964335814","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4249048193","https://openalex.org/W3000360420","https://openalex.org/W3172144307","https://openalex.org/W3184247917","https://openalex.org/W4235657630","https://openalex.org/W2331401504","https://openalex.org/W2620283452","https://openalex.org/W2038219622","https://openalex.org/W566381545","https://openalex.org/W2342291550"],"abstract_inverted_index":{"Recently,":[0],"string":[1,39,50,156],"kernels":[2,157],"have":[3],"obtained":[4],"stateof-the-art":[5],"results":[6,37],"in":[7,55,61,149,168],"various":[8],"text":[9],"classification":[10,171],"tasks":[11],"such":[12],"as":[13,65,98],"Arabic":[14,173],"dialect":[15,174],"identification":[16],"or":[17],"native":[18],"language":[19],"identification.":[20,175],"In":[21,80,100],"this":[22],"paper,":[23],"we":[24,141,162],"apply":[25],"two":[26,77],"simple":[27,72],"yet":[28],"effective":[29],"transductive":[30],"learning":[31,78],"approaches":[32],"to":[33,119,158],"further":[34],"improve":[35],"the":[36,48,56,62,81,89,95,101,111,120,129,133,143,147,150,159],"of":[38,106,126,132],"kernels.":[40],"The":[41],"first":[42,82,151],"approach":[43,69],"is":[44,70,86],"based":[45,75],"on":[46,76,88,94],"interpreting":[47],"pairwise":[49],"kernel":[51],"similarities":[52],"between":[53],"samples":[54,60,108,136],"training":[57,90,121,152],"set":[58,64,91,122],"and":[59,92,172],"test":[63,96,107,135,160],"features.":[66],"Our":[67],"second":[68,102],"a":[71,84,104],"self-training":[73],"method":[74],"iterations.":[79],"iteration,":[83,103],"classifier":[85,112,148],"trained":[87],"tested":[93],"set,":[97,161],"usual.":[99],"number":[105],"(to":[109],"which":[110],"associated":[113],"higher":[114],"confidence":[115],"scores)":[116],"are":[117,137],"added":[118,134],"for":[123],"another":[124],"round":[125],"training.":[127],"However,":[128],"ground-truth":[130],"labels":[131,144],"not":[138],"necessary.":[139],"Instead,":[140],"use":[142],"predicted":[145],"by":[146],"iteration.":[153],"By":[154],"adapting":[155],"report":[163],"significantly":[164],"better":[165],"accuracy":[166],"rates":[167],"English":[169],"polarity":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}