Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-23889
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ulasik, Malgorzata Anna | - |
dc.contributor.author | Hürlimann, Manuela | - |
dc.contributor.author | Dubel, Bogumila | - |
dc.contributor.author | Kaufmann, Yves | - |
dc.contributor.author | Rudolf, Silas | - |
dc.contributor.author | Deriu, Jan Milan | - |
dc.contributor.author | Mlynchyk, Katsiaryna | - |
dc.contributor.author | Hutter, Hans-Peter | - |
dc.contributor.author | Cieliebak, Mark | - |
dc.date.accessioned | 2022-01-12T14:45:43Z | - |
dc.date.available | 2022-01-12T14:45:43Z | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 1613-0073 | de_CH |
dc.identifier.uri | http://ceur-ws.org/Vol-2957/sg_paper3.pdf | de_CH |
dc.identifier.uri | https://digitalcollection.zhaw.ch/handle/11475/23889 | - |
dc.description.abstract | This paper presents the contribution of ZHAW-CAI to the Shared Task ”Swiss German Speech to Standard German Text” at the SwissText 2021 conference. Our approach combines three models based on the Fairseq, Jasper and Wav2vec architectures trained on multilingual, German and Swiss German data. We applied an ensembling algorithm on the predictions of the three models in order to retrieve the most reliable candidate out of the provided translations for each spoken utterance. With the ensembling output, we achieved a BLEU score of 39.39 on the private test set, which gave us the third place out of four contributors in the competition. | de_CH |
dc.language.iso | en | de_CH |
dc.publisher | CEUR Workshop Proceedings | de_CH |
dc.rights | http://creativecommons.org/licenses/by/4.0/ | de_CH |
dc.subject | Natural language processing | de_CH |
dc.subject | Swiss German | de_CH |
dc.subject.ddc | 006: Spezielle Computerverfahren | de_CH |
dc.subject.ddc | 410.285: Computerlinguistik | de_CH |
dc.title | ZHAW-CAI : ensemble method for Swiss German speech to Standard German text | de_CH |
dc.type | Konferenz: Paper | de_CH |
dcterms.type | Text | de_CH |
zhaw.departement | Angewandte Linguistik | de_CH |
zhaw.departement | School of Engineering | de_CH |
zhaw.organisationalunit | Centre for Artificial Intelligence (CAI) | de_CH |
zhaw.organisationalunit | Institute of Language Competence (ILC) | de_CH |
dc.identifier.doi | 10.21256/zhaw-23889 | - |
zhaw.conference.details | Swiss Text Analytics Conference – SwissText 2021, Online, 14-16 June 2021 | de_CH |
zhaw.funding.eu | No | de_CH |
zhaw.originated.zhaw | Yes | de_CH |
zhaw.parentwork.editor | Benites de Azevedo e Souza, Fernando | - |
zhaw.parentwork.editor | Tuggener, Don | - |
zhaw.parentwork.editor | Hürlimann, Manuela | - |
zhaw.parentwork.editor | Cieliebak, Mark | - |
zhaw.parentwork.editor | Vogel, Manfred | - |
zhaw.publication.status | publishedVersion | de_CH |
zhaw.publication.review | Editorial review | de_CH |
zhaw.title.proceedings | Proceedings of the Swiss Text Analytics Conference 2021 | de_CH |
zhaw.webfeed | Datalab | de_CH |
zhaw.webfeed | Digital Linguistics | de_CH |
zhaw.webfeed | Natural Language Processing | de_CH |
zhaw.webfeed | ZHAW digital | de_CH |
zhaw.funding.zhaw | Interscriber: Turning Dialogues into Actionable Insights | de_CH |
zhaw.author.additional | No | de_CH |
zhaw.display.portrait | Yes | de_CH |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2021_Ulasik-etal_ZHAW-CAI-Ensemble-method-Swiss-Standard-German.pdf | 241.79 kB | Adobe PDF | View/Open |
Show simple item record
Ulasik, M. A., Hürlimann, M., Dubel, B., Kaufmann, Y., Rudolf, S., Deriu, J. M., Mlynchyk, K., Hutter, H.-P., & Cieliebak, M. (2021). ZHAW-CAI : ensemble method for Swiss German speech to Standard German text [Conference paper]. In F. Benites de Azevedo e Souza, D. Tuggener, M. Hürlimann, M. Cieliebak, & M. Vogel (Eds.), Proceedings of the Swiss Text Analytics Conference 2021. CEUR Workshop Proceedings. https://doi.org/10.21256/zhaw-23889
Ulasik, M.A. et al. (2021) ‘ZHAW-CAI : ensemble method for Swiss German speech to Standard German text’, in F. Benites de Azevedo e Souza et al. (eds) Proceedings of the Swiss Text Analytics Conference 2021. CEUR Workshop Proceedings. Available at: https://doi.org/10.21256/zhaw-23889.
M. A. Ulasik et al., “ZHAW-CAI : ensemble method for Swiss German speech to Standard German text,” in Proceedings of the Swiss Text Analytics Conference 2021, 2021. doi: 10.21256/zhaw-23889.
ULASIK, Malgorzata Anna, Manuela HÜRLIMANN, Bogumila DUBEL, Yves KAUFMANN, Silas RUDOLF, Jan Milan DERIU, Katsiaryna MLYNCHYK, Hans-Peter HUTTER und Mark CIELIEBAK, 2021. ZHAW-CAI : ensemble method for Swiss German speech to Standard German text. In: Fernando BENITES DE AZEVEDO E SOUZA, Don TUGGENER, Manuela HÜRLIMANN, Mark CIELIEBAK und Manfred VOGEL (Hrsg.), Proceedings of the Swiss Text Analytics Conference 2021 [online]. Conference paper. CEUR Workshop Proceedings. 2021. Verfügbar unter: http://ceur-ws.org/Vol-2957/sg_paper3.pdf
Ulasik, Malgorzata Anna, Manuela Hürlimann, Bogumila Dubel, Yves Kaufmann, Silas Rudolf, Jan Milan Deriu, Katsiaryna Mlynchyk, Hans-Peter Hutter, and Mark Cieliebak. 2021. “ZHAW-CAI : Ensemble Method for Swiss German Speech to Standard German Text.” Conference paper. In Proceedings of the Swiss Text Analytics Conference 2021, edited by Fernando Benites de Azevedo e Souza, Don Tuggener, Manuela Hürlimann, Mark Cieliebak, and Manfred Vogel. CEUR Workshop Proceedings. https://doi.org/10.21256/zhaw-23889.
Ulasik, Malgorzata Anna, et al. “ZHAW-CAI : Ensemble Method for Swiss German Speech to Standard German Text.” Proceedings of the Swiss Text Analytics Conference 2021, edited by Fernando Benites de Azevedo e Souza et al., CEUR Workshop Proceedings, 2021, https://doi.org/10.21256/zhaw-23889.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.