{"id":"https://openalex.org/W2602867757","doi":null,"title":"Automatic normalisation of the Swiss German ArchiMob corpus using character-level machine translation","display_name":"Automatic normalisation of the Swiss German ArchiMob corpus using character-level machine translation","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2602867757","mag":"2602867757"},"language":"en","primary_location":{"id":"pmh:oai:unige.ch:aou:unige:90846","doi":null,"is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:90846","pdf_url":null,"source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proceedings of the 13th Conference on Natural Language Processing (KONVENS) / Dipper, S., Neubarth, F. & Zinsmeister , H. (ed.), (2016) p. 248-255","raw_type":"ConferencePaper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://archive-ouverte.unige.ch/unige:90846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063672760","display_name":"Yves Scherrer","orcid":"https://orcid.org/0000-0001-5247-5073","observed_orcids":["https://orcid.org/0000-0001-5247-5073"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yves Scherrer","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5247-5073","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021557805","display_name":"Nikola Ljube\u0161i\u0107","orcid":"https://orcid.org/0000-0001-7169-9152","observed_orcids":["https://orcid.org/0000-0001-7169-9152"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikola Ljube\u0161i\u0107","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7169-9152","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4382,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92870183,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9643999934196472,"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":0.9643999934196472,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.024900000542402267,"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":0.003599999938160181,"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/swiss-german","display_name":"Swiss German dialects","score":0.6140000224113464},{"id":"https://openalex.org/keywords/dialect-variation","display_name":"dialect variation","score":0.5189999938011169},{"id":"https://openalex.org/keywords/intra-speaker-variation","display_name":"intra-speaker variation","score":0.8560000061988831},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.8549817800521851},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7487226128578186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256738543510437},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7111946940422058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7027225494384766},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6774723529815674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5885475873947144},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.49375900626182556},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.434243381023407},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4060332775115967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37165406346321106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1039116382598877},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:unige.ch:aou:unige:90846","doi":null,"is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:90846","pdf_url":null,"source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proceedings of the 13th Conference on Natural Language Processing (KONVENS) / Dipper, S., Neubarth, F. & Zinsmeister , H. (ed.), (2016) p. 248-255","raw_type":"ConferencePaper"},{"id":"pmh:oai:unige.ch:unige:90846","doi":null,"is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:90846","pdf_url":"https://archive-ouverte.unige.ch/unige:90846","source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 13th Conference on Natural Language Processing (KONVENS)","raw_type":"info:eu-repo/semantics/bookPart"},{"id":"mag:2602867757","doi":null,"is_oa":false,"landing_page_url":"https://www.linguistics.rub.de/konvens16/pub/32_konvensproc.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306517563","display_name":"KONVENS","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":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"KONVENS","raw_type":null}],"best_oa_location":{"id":"pmh:oai:unige.ch:aou:unige:90846","doi":null,"is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:90846","pdf_url":null,"source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proceedings of the 13th Conference on Natural Language Processing (KONVENS) / Dipper, S., Neubarth, F. & Zinsmeister , H. (ed.), (2016) p. 248-255","raw_type":"ConferencePaper"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3331211887","display_name":"Regional Linguistic Data Initiative","funder_award_id":"160501","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320323874","display_name":"Universit\u00e4t Z\u00fcrich","ror":"https://ror.org/02crff812"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2602867757.pdf","grobid_xml":"https://content.openalex.org/works/W2602867757.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W164595361","https://openalex.org/W214028658","https://openalex.org/W1553878378","https://openalex.org/W2116599427","https://openalex.org/W2124807415","https://openalex.org/W2134800885","https://openalex.org/W2135716572","https://openalex.org/W2251378216","https://openalex.org/W2251463342","https://openalex.org/W2251969247","https://openalex.org/W2403864882","https://openalex.org/W2575880437"],"related_works":["https://openalex.org/W2978315399","https://openalex.org/W2963967291","https://openalex.org/W2575880437","https://openalex.org/W4389518652","https://openalex.org/W2969821524","https://openalex.org/W4385895930","https://openalex.org/W2938765499","https://openalex.org/W2397927934","https://openalex.org/W2251703700","https://openalex.org/W4389157044"],"abstract_inverted_index":{"The":[0],"Swiss":[1],"German":[2],"dialect":[3],"corpus":[4,12],"ArchiMob":[5],"poses":[6],"great":[7],"challenges":[8],"for":[9],"NLP":[10],"and":[11,33,80,105],"linguistic":[13],"research":[14],"due":[15],"to":[16,53,58,87,90],"the":[17,24,42,60],"massive":[18],"amount":[19],"of":[20,44,74,78,92,99,106],"variation":[21,27,32,38],"found":[22],"in":[23],"transcriptions:":[25],"dialectal":[26],"is":[28,39,85],"combined":[29],"with":[30,34],"intra-speaker":[31],"transcriber":[35],"inconsistencies.":[36],"This":[37],"reduced":[40],"through":[41],"addition":[43],"a":[45,66,102,109],"normalisation":[46,61,94],"layer.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"use":[54],"character-level":[55,67],"machine":[56,68],"translation":[57,69],"learn":[59],"process.":[62],"We":[63],"show":[64],"that":[65],"system":[70,111],"trained":[71],"on":[72],"pairs":[73,77],"segments":[75],"(not":[76],"words)":[79],"including":[81],"multiple":[82],"language":[83],"models":[84],"able":[86],"achieve":[88],"up":[89],"90.46%":[91],"word":[93],"accuracy,":[95],"an":[96],"error":[97],"reduction":[98],"45%":[100],"over":[101,108],"strong":[103],"baseline":[104],"34%":[107],"heterogeneous":[110],"proposed":[112],"by":[113],"Samardzic":[114],"et":[115],"al.":[116],"(2015).":[117]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-04-07T00:00:00"}
