Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vamvas, Jannis, Aepli, Noëmi, Sennrich, Rico
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917574723239936
author Vamvas, Jannis
Aepli, Noëmi
Sennrich, Rico
author_facet Vamvas, Jannis
Aepli, Noëmi
Sennrich, Rico
contents Creating neural text encoders for written Swiss German is challenging due to a dearth of training data combined with dialectal variation. In this paper, we build on several existing multilingual encoders and adapt them to Swiss German using continued pre-training. Evaluation on three diverse downstream tasks shows that simply adding a Swiss German adapter to a modular encoder achieves 97.5% of fully monolithic adaptation performance. We further find that for the task of retrieving Swiss German sentences given Standard German queries, adapting a character-level model is more effective than the other adaptation strategies. We release our code and the models trained for our experiments at https://github.com/ZurichNLP/swiss-german-text-encoders
format Preprint
id arxiv_https___arxiv_org_abs_2401_14400
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect
Vamvas, Jannis
Aepli, Noëmi
Sennrich, Rico
Computation and Language
Creating neural text encoders for written Swiss German is challenging due to a dearth of training data combined with dialectal variation. In this paper, we build on several existing multilingual encoders and adapt them to Swiss German using continued pre-training. Evaluation on three diverse downstream tasks shows that simply adding a Swiss German adapter to a modular encoder achieves 97.5% of fully monolithic adaptation performance. We further find that for the task of retrieving Swiss German sentences given Standard German queries, adapting a character-level model is more effective than the other adaptation strategies. We release our code and the models trained for our experiments at https://github.com/ZurichNLP/swiss-german-text-encoders
title Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect
topic Computation and Language
url https://arxiv.org/abs/2401.14400