Publication: Fine-tuning the SwissBERT Encoder Model for Embedding Sentences and Documents
Fine-tuning the SwissBERT Encoder Model for Embedding Sentences and Documents
Date
Date
Date
Citations
Grosjean, J. L. (2024). Fine-tuning the SwissBERT Encoder Model for Embedding Sentences and Documents. (Master’s thesis, University of Zurich) https://doi.org/10.5167/uzh-262549
Abstract
Abstract
Abstract
Encoder models trained for the embedding of sentences or short documents have proven useful for tasks such as semantic search and topic modeling. In this paper, a version of the SwissBERT encoder model specifically fine-tuned for this purpose is presented. SwissBERT contains language adapters for the four national languages of Switzerland – German, French, Italian, and Romansh – and has been pre-trained on a large number of news articles in those languages. Using contrastive learn- ing based on a subset of the original training datase
Metrics
Downloads
Views
Citations
Additional indexing
Creators (Authors)
Faculty
Faculty
Faculty
Item Type
Item Type
Item Type
Referees
In collections
Dewey Decimal Classifikation
Dewey Decimal Classifikation
Dewey Decimal Classifikation
Language
Language
Language
Publication date
Publication date
Publication date
Date available
Date available
Date available
OA Status
OA Status
OA Status
Metrics
Downloads
Views
Citations
Citations
Grosjean, J. L. (2024). Fine-tuning the SwissBERT Encoder Model for Embedding Sentences and Documents. (Master’s thesis, University of Zurich) https://doi.org/10.5167/uzh-262549
