{"id":"https://openalex.org/W3113574778","doi":"https://doi.org/10.18653/v1/2020.coling-main.89","title":"Context-Aware Text Normalisation for Historical Dialects","display_name":"Context-Aware Text Normalisation for Historical Dialects","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3113574778","doi":"https://doi.org/10.18653/v1/2020.coling-main.89","mag":"3113574778"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.89","pdf_url":null,"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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2020.coling-main.89","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040300223","display_name":"Maria Sukhareva","orcid":"https://orcid.org/0009-0000-1952-8727"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maria Sukhareva","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040300223"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17281315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1023","last_page":"1036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9857000112533569,"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":0.8015362024307251},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7545739412307739},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7059208154678345},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6684887409210205},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6158514022827148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6107212901115417},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.572458803653717},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.5630018711090088},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5323526859283447},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5226500034332275},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47843387722969055},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4537336230278015},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4311315417289734},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17349213361740112},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1486474573612213},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.10116860270500183},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0742984414100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015362024307251},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7545739412307739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7059208154678345},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6684887409210205},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6158514022827148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6107212901115417},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.572458803653717},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.5630018711090088},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5323526859283447},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5226500034332275},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47843387722969055},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4537336230278015},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4311315417289734},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17349213361740112},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1486474573612213},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.10116860270500183},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0742984414100647},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.89","pdf_url":null,"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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.89","pdf_url":null,"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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W105720630","https://openalex.org/W130632585","https://openalex.org/W779297117","https://openalex.org/W2085809856","https://openalex.org/W2105585206","https://openalex.org/W2117717100","https://openalex.org/W2118947254","https://openalex.org/W2251463342","https://openalex.org/W2550821151","https://openalex.org/W2625023053","https://openalex.org/W2778814079","https://openalex.org/W2945656493","https://openalex.org/W2945958591","https://openalex.org/W2950176361","https://openalex.org/W2952446148","https://openalex.org/W2962712961","https://openalex.org/W2963715460","https://openalex.org/W2963805136","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2912615426","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W1964944391","https://openalex.org/W2104166387","https://openalex.org/W2372385138","https://openalex.org/W2794347674"],"abstract_inverted_index":{"Context-aware":[0],"historical":[1,68],"text":[2],"normalisation":[3,17,60],"is":[4,54,137],"a":[5,15,34,38,48,112],"severely":[6],"under-researched":[7],"area.":[8],"To":[9],"fill":[10],"the":[11,22,42,57,67,84,93,102,119,129,135],"gap":[12],"we":[13,110],"propose":[14,33],"context-aware":[16,39,96],"approach":[18],"that":[19,53,79],"relies":[20,46],"on":[21,47,66,91],"state-of-the-art":[23],"methods":[24],"in":[25,118],"neural":[26],"machine":[27],"translation":[28],"and":[29,75],"transfer":[30],"learning.":[31],"We":[32,77],"multidialect":[35,69],"normaliser":[36],"with":[37,128],"reranking":[40,97],"of":[41,71,107],"candidates.":[43,61],"The":[44,62,95,122,132],"reranker":[45,136],"word-level":[49],"n-gram":[50],"language":[51],"model":[52],"applied":[55],"to":[56,87],"five":[58],"best":[59],"results":[63,125],"are":[64,126],"evaluated":[65],"datasets":[70],"German,":[72],"Spanish,":[73],"Portuguese":[74],"Slovene.":[76],"show":[78],"incorporating":[80],"dialectal":[81],"information":[82],"into":[83],"training":[85],"leads":[86],"an":[88],"accuracy":[89,115],"improvement":[90,100],"all":[92],"datasets.":[94],"gives":[98],"further":[99],"over":[101],"baseline.":[103],"For":[104],"three":[105,124],"out":[106],"six":[108],"datasets,":[109],"reach":[111],"significantly":[113],"higher":[114],"than":[116],"reported":[117],"previous":[120],"studies.":[121],"other":[123],"comparable":[127],"current":[130],"state-of-the-art.":[131],"code":[133],"for":[134],"published":[138],"as":[139],"open-source.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}