{"id":"https://openalex.org/W2953006368","doi":"https://doi.org/10.18653/v1/p19-2037","title":"Normalizing Non-canonical Turkish Texts Using Machine Translation Approaches","display_name":"Normalizing Non-canonical Turkish Texts Using Machine Translation Approaches","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2953006368","doi":"https://doi.org/10.18653/v1/p19-2037","mag":"2953006368"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-2037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-2037","pdf_url":"https://www.aclweb.org/anthology/P19-2037.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 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-2037.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069570906","display_name":"Talha \u00c7olako\u011flu","orcid":"https://orcid.org/0000-0002-4524-862X"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Talha \u00c7olako\u011flu","raw_affiliation_strings":["Istanbul Technical University Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istanbul Technical University Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060871343","display_name":"Umut Sulubacak","orcid":"https://orcid.org/0000-0002-4929-4850"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Umut Sulubacak","raw_affiliation_strings":["University of Helsinki Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086282318","display_name":"A. C\u00fcneyd Tantu\u011f","orcid":"https://orcid.org/0000-0003-0524-3397"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ahmet C\u00fcneyd Tantu\u011f","raw_affiliation_strings":["Istanbul Technical University Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istanbul Technical University Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069570906"],"corresponding_institution_ids":["https://openalex.org/I48912391"],"apc_list":null,"apc_paid":null,"fwci":1.7417,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88646589,"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":"267","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9830999970436096,"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/turkish","display_name":"Turkish","score":0.7608492374420166},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7288114428520203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6850746273994446},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.639614462852478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4974067509174347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49042031168937683},{"id":"https://openalex.org/keywords/non-canonical","display_name":"Non canonical","score":0.48947107791900635},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23071810603141785},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08299577236175537},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0645148754119873}],"concepts":[{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.7608492374420166},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7288114428520203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6850746273994446},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.639614462852478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4974067509174347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49042031168937683},{"id":"https://openalex.org/C3018844941","wikidata":"https://www.wikidata.org/wiki/Q6718887","display_name":"Non canonical","level":2,"score":0.48947107791900635},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23071810603141785},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08299577236175537},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0645148754119873},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C95444343","wikidata":"https://www.wikidata.org/wiki/Q7141","display_name":"Cell biology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/p19-2037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-2037","pdf_url":"https://www.aclweb.org/anthology/P19-2037.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 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/305143","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/305143","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},{"id":"pmh:oai:polen.itu.edu.tr:11527/49440","is_oa":false,"landing_page_url":"https://hdl.handle.net/11527/49440","pdf_url":null,"source":{"id":"https://openalex.org/S4306400460","display_name":"Istanbul Technical University Academic Open Archive (Istanbul Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48912391","host_organization_name":"Istanbul Technical University","host_organization_lineage":["https://openalex.org/I48912391"],"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":"Article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-2037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-2037","pdf_url":"https://www.aclweb.org/anthology/P19-2037.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 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310086","display_name":"Helsingin Yliopisto","ror":"https://ror.org/040af2s02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953006368.pdf","grobid_xml":"https://content.openalex.org/works/W2953006368.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W619445499","https://openalex.org/W629021723","https://openalex.org/W630532510","https://openalex.org/W2004316800","https://openalex.org/W2066201260","https://openalex.org/W2080373976","https://openalex.org/W2107221152","https://openalex.org/W2117717100","https://openalex.org/W2124807415","https://openalex.org/W2134800885","https://openalex.org/W2250738918","https://openalex.org/W2251448372","https://openalex.org/W2252080608","https://openalex.org/W2397927934","https://openalex.org/W2419539795","https://openalex.org/W2566903391","https://openalex.org/W2595715041","https://openalex.org/W2602867757","https://openalex.org/W2621251601","https://openalex.org/W2737886250","https://openalex.org/W2759029195","https://openalex.org/W2903792317","https://openalex.org/W2950607315","https://openalex.org/W2963212250","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W2557742235"],"abstract_inverted_index":{"With":[0],"the":[1,4,37,88],"growth":[2],"of":[3,27,36,45,49,72,78],"social":[5],"web,":[6],"usergenerated":[7],"text":[8,15,41],"data":[9,29],"has":[10],"reached":[11],"unprecedented":[12],"sizes.":[13],"Non-canonical":[14],"normalization":[16,42],"provides":[17],"a":[18,24,46,63,93],"way":[19],"to":[20,86],"exploit":[21],"this":[22],"as":[23],"practical":[25],"source":[26],"training":[28],"for":[30],"language":[31],"processing":[32],"systems.":[33],"The":[34],"state":[35],"art":[38],"in":[39],"Turkish":[40],"is":[43],"composed":[44],"tokenlevel":[47],"pipeline":[48],"modules,":[50],"heavily":[51],"dependent":[52],"on":[53],"external":[54],"linguistic":[55],"resources":[56],"and":[57],"manuallydefined":[58],"rules.":[59],"Instead,":[60],"we":[61,83],"propose":[62],"fullyautomated,":[64],"context-aware":[65],"machine":[66],"translation":[67],"approach":[68,80],"with":[69,75],"fewer":[70],"stages":[71],"processing.":[73],"Experiments":[74],"various":[76],"implementations":[77],"our":[79],"show":[81],"that":[82],"are":[84],"able":[85],"surpass":[87],"current":[89],"best-performing":[90],"system":[91],"by":[92],"large":[94],"margin.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}
