{"id":"https://openalex.org/W2741365501","doi":"https://doi.org/10.18653/v1/w17-1221","title":"CLUZH at VarDial GDI 2017: Testing a Variety of Machine Learning Tools for the Classification of Swiss German Dialects","display_name":"CLUZH at VarDial GDI 2017: Testing a Variety of Machine Learning Tools for the Classification of Swiss German Dialects","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741365501","doi":"https://doi.org/10.18653/v1/w17-1221","mag":"2741365501"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1221","pdf_url":"https://www.aclweb.org/anthology/W17-1221.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 Fourth Workshop on NLP for Similar Languages,\n          Varieties and Dialects (VarDial)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-1221.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073027507","display_name":"Simon Clematide","orcid":"https://orcid.org/0000-0003-1365-0662"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Simon Clematide","raw_affiliation_strings":["Institute of Computational Linguistics University of Zurich"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089340248","display_name":"Peter Makarov","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peter Makarov","raw_affiliation_strings":["Institute of Computational Linguistics University of Zurich"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073027507"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":2.5109,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91805264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9972000122070312,"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":0.9919000267982483,"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/support-vector-machine","display_name":"Support vector machine","score":0.82248455286026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7124547362327576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.71245276927948},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6829007267951965},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6563733220100403},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6441569328308105},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6324637532234192},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5903507471084595},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5732774138450623},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.572853684425354},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.539590060710907},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4481217861175537},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4398949146270752},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.41411516070365906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3370036482810974},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1577741503715515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11303487420082092},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06216815114021301}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.82248455286026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124547362327576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.71245276927948},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6829007267951965},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6563733220100403},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6441569328308105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6324637532234192},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5903507471084595},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5732774138450623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.572853684425354},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.539590060710907},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4481217861175537},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4398949146270752},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.41411516070365906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3370036482810974},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1577741503715515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11303487420082092},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06216815114021301},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w17-1221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1221","pdf_url":"https://www.aclweb.org/anthology/W17-1221.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 Fourth Workshop on NLP for Similar Languages,\n          Varieties and Dialects (VarDial)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:148682","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"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":"Clematide, Simon; Makarov, Peter  (2017). CLUZH at VarDial GDI 2017: Testing a Variety of Machine Learning Tools for the Classification of Swiss German Dialects.  In: Fourth Workshop on NLP for Similar Languages, Varieties and Dialects, Valencia, 3 April 2017. Association for Computational Linguistics, 170-177.","raw_type":"Conference or Workshop Item"},{"id":"doi:10.5167/uzh-148682","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-148682","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/w17-1221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1221","pdf_url":"https://www.aclweb.org/anthology/W17-1221.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 Fourth Workshop on NLP for Similar Languages,\n          Varieties and Dialects (VarDial)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741365501.pdf","grobid_xml":"https://content.openalex.org/works/W2741365501.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W617617351","https://openalex.org/W1556664388","https://openalex.org/W2051434435","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2111362445","https://openalex.org/W2112483442","https://openalex.org/W2118020653","https://openalex.org/W2122825543","https://openalex.org/W2129999749","https://openalex.org/W2160986985","https://openalex.org/W2170240176","https://openalex.org/W2252335727","https://openalex.org/W2561747913","https://openalex.org/W2575880437","https://openalex.org/W2620806258","https://openalex.org/W2811380766","https://openalex.org/W2963012544","https://openalex.org/W4211191796"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2347460059","https://openalex.org/W2111726165","https://openalex.org/W1984858032","https://openalex.org/W2537862391","https://openalex.org/W2417174640"],"abstract_inverted_index":{"Our":[0,28],"submissions":[1],"for":[2],"the":[3,9,43,67,95],"GDI":[4],"2017":[5],"Shared":[6],"Task":[7],"are":[8],"results":[10],"from":[11],"three":[12],"different":[13],"types":[14],"of":[15,36],"classifiers:":[16],"Nave":[17],"Bayes,":[18,56],"Conditional":[19],"Random":[20],"Fields":[21],"(CRF),":[22],"and":[23],"Support":[24],"Vector":[25],"Machine":[26],"(SVM).":[27],"CRF-based":[29],"run":[30,54],"achieves":[31],"a":[32],"weighted":[33],"F1":[34],"score":[35],"65%":[37],"(third":[38],"rank)":[39,62],"being":[40,63],"beaten":[41],"by":[42,46,49],"best":[44,68],"system":[45],"0.9%.":[47],"Measured":[48],"classification":[50],"accuracy,":[51],"our":[52,73,86],"ensemble":[53],"(Nave":[55],"CRF,":[57],"SVM)":[58],"reaches":[59],"67%":[60],"(second":[61],"1%":[64],"lower":[65],"than":[66,85],"system.":[69],"We":[70],"also":[71],"describe":[72],"experiments":[74],"with":[75],"Recurrent":[76],"Neural":[77],"Network":[78],"(RNN)":[79],"architectures.":[80],"Since":[81],"they":[82],"performed":[83],"worse":[84],"nonneural":[87],"approaches":[88],"we":[89],"did":[90],"not":[91],"include":[92],"them":[93],"in":[94],"submission.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}