Hauptthemen unserer Publikationen zu Schweizerdeutsch:
2022
Proceedings Articles
Plüss, Michel; Hürlimann, Manuela; Cuny, Marc; Stockli, Alla; Kapotis, Nikolaos; Hartmann, Julia; Ulasik, Malgorzata Anna; Scheller, Christian; Schraner, Yanick; Jain, Amit; Deriu, Jan; Cieliebak, Mark; Vogel, Manfred
SDS-200: A Swiss German Speech to Standard German Text Corpus Proceedings Article
In: 13th International Conference on Language Resources,; (LREC), Evaluation (Hrsg.): 2022.
Links | BibTeX | Schlagwörter: Corpus, Endangered Languages, Less-Resourced Languages, Speech Recognition/Understanding, Statistical and Machine Learning Methods
@inproceedings{,
title = {SDS-200: A Swiss German Speech to Standard German Text Corpus},
author = {Michel Plüss and Manuela Hürlimann and Marc Cuny and Alla Stockli and Nikolaos Kapotis and Julia Hartmann and Malgorzata Anna Ulasik and Christian Scheller and Yanick Schraner and Amit Jain and Jan Deriu and Mark Cieliebak and Manfred Vogel},
editor = {13th International Conference on Language Resources and Evaluation (LREC)},
url = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.347.pdf
https://doi.org/10.48550/arXiv.2205.09501},
doi = {10.48550/arXiv.2205.09501},
year = {2022},
date = {2022-05-19},
urldate = {2022-05-19},
keywords = {Corpus, Endangered Languages, Less-Resourced Languages, Speech Recognition/Understanding, Statistical and Machine Learning Methods},
pubstate = {published},
tppubtype = {inproceedings}
}
2020
Proceedings Articles
Benites, Fernando; Hürlimann, Manuela; von Däniken, Pius; Cieliebak, Mark
ZHAW-InIT – Social Media Geolocation at VarDial 2020 Proceedings Article
In: on Computational Linguistics (ICCL), International Committee (Hrsg.): S. 254–264, International Committee on Computational Linguistics (ICCL), Barcelona, Spain (Online), 2020.
Abstract | Links | BibTeX | Schlagwörter: Endangered Languages, Geolocation, Less-Resourced Languages, Speech Recognition/Understanding
@inproceedings{nokey,
title = {ZHAW-InIT – Social Media Geolocation at VarDial 2020},
author = {Fernando Benites and Manuela Hürlimann and Pius von Däniken and Mark Cieliebak},
editor = {International Committee on Computational Linguistics (ICCL)},
url = {https://aclanthology.org/2020.vardial-1.24
https://aclanthology.org/2020.vardial-1.24.pdf},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
pages = {254–264},
publisher = {International Committee on Computational Linguistics (ICCL)},
address = {Barcelona, Spain (Online)},
abstract = {We describe our approaches for the Social Media Geolocation (SMG) task at the VarDial Evaluation Campaign 2020. The goal was to predict geographical location (latitudes and longitudes) given an input text. There were three subtasks corresponding to German-speaking Switzerland (CH), Germany and Austria (DE-AT), and Croatia, Bosnia and Herzegovina, Montenegro and Serbia (BCMS). We submitted solutions to all subtasks but focused our development efforts on the CH subtask, where we achieved third place out of 16 submissions with a median distance of 15.93 km and had the best result of 14 unconstrained systems. In the DE-AT subtask, we ranked sixth out of ten submissions (fourth of 8 unconstrained systems) and for BCMS we achieved fourth place out of 13 submissions (second of 11 unconstrained systems).},
keywords = {Endangered Languages, Geolocation, Less-Resourced Languages, Speech Recognition/Understanding},
pubstate = {published},
tppubtype = {inproceedings}
}
Forschungsberichte
von Däniken, Pius; Hürlimann, Manuela; Cieliebak, Mark
Overview of the GermEval 2020 Shared Task on Swiss German Language Identification Forschungsbericht
2020.
Abstract | Links | BibTeX | Schlagwörter: Endangered Languages, Less-Resourced Languages
@techreport{nokey,
title = {Overview of the GermEval 2020 Shared Task on Swiss German Language Identification},
author = {Pius von Däniken and Manuela Hürlimann and Mark Cieliebak},
editor = {Institute of Applied Information Technology
Zurich University of Applied Sciences},
url = {https://ceur-ws.org/Vol-2624/germeval-task2-paper1.pdf},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
abstract = {In this paper, we present the findings of the Shared Task on Swiss German Language Identification organised as part of the 7th edition of GermEval, co-located with SwissText and KONVENS 2020.},
keywords = {Endangered Languages, Less-Resourced Languages},
pubstate = {published},
tppubtype = {techreport}
}
2018
Proceedings Articles
Grubenmann, Ralf; Tuggener, Don; von Däniken, Pius; Deriu, Jan; Cieliebak, Mark
SB-CH: A Swiss German Corpus with Sentiment Annotations Proceedings Article
In: 11th International Conference on Language Resources,; (LREC), Evaluation (Hrsg.): 2018, ISBN: 979-10-95546-00-9.
Links | BibTeX | Schlagwörter: Corpus, Endangered Languages, Less-Resourced Languages, sentiment annotation
@inproceedings{nokey,
title = {SB-CH: A Swiss German Corpus with Sentiment Annotations},
author = {Ralf Grubenmann and Don Tuggener and Pius von Däniken and Jan Deriu and Mark Cieliebak},
editor = {11th International Conference on Language Resources and Evaluation (LREC)},
url = {https://digitalcollection.zhaw.ch/handle/11475/10819},
isbn = {979-10-95546-00-9},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
keywords = {Corpus, Endangered Languages, Less-Resourced Languages, sentiment annotation},
pubstate = {published},
tppubtype = {inproceedings}
}
Forschungsberichte
Samardžić, Tanja; Cieliebak, Mark; Deriu, Jan
Future Actions for Swiss German — Workshop Results at SwissText 2018 Forschungsbericht
2018.
Abstract | Links | BibTeX | Schlagwörter: Endangered Languages, Less-Resourced Languages
@techreport{nokey,
title = {Future Actions for Swiss German — Workshop Results at SwissText 2018},
author = {Tanja Samardžić and Mark Cieliebak and Jan Deriu},
url = {https://ceur-ws.org/Vol-2226/paper12.pdf},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
abstract = {The goal of this workshop was to initiate collaborations among companies and academic institutions for developing Swiss German resources and activities. The need for such an initiative is created by a growing interest for applying automatic text processing technologies to Swiss German, which takes place in the context of particularly scarce data sets. We have considered potential modes for a collaborative data development and management. The outcome of the workshop are defined common interests, priorities, and the first steps in future synchronised efforts.},
keywords = {Endangered Languages, Less-Resourced Languages},
pubstate = {published},
tppubtype = {techreport}
}