NCHLT Xitsonga RoBERTa language model
| Title | NCHLT Xitsonga RoBERTa language model |
| Description | Contextual masked language model based on the RoBERTa architecture (Liu et al., 2019). The model is trained as a masked language model and not fine-tuned for any downstream process. The model can be used both as a masked LM or as an embedding model to provide real-valued vectorised respresentations of words or string sequences for Xitsonga text. |
| Contact name | Roald Eiselen |
| Contact email | Roald.Eiselen@nwu.ac.za |
| Publisher(s) | North-West University; Centre for Text Technology (CTexT) |
| License | Creative Commons Attribution 4.0 International (CC-BY 4.0) |
| Language(s) | Xitsonga |
| Author(s) | Roald Eiselen |
| Contributor | Rico Koen; Albertus Kruger; Jacques van Heerden |
| URI | https://hdl.handle.net/20.500.12185/617 |
| Media type | Text |
| Type | Modules |
| Media category | Language model |
| Format extent | Training data: Paragraphs: 360,698; Token count: 7,357,764; Vocab size: 30,000; Embedding dimensions: 768; |
| Format size | 235.98MB (Zipped) |
| Project | NCHLT Text IV |
| Software requirements | Python |
| Source | Web; Government Documents |
| ISO639 code | ts |
| Submit date | 2023-07-26T15:16:25Z; 2023-05-01 |
| Date available | 2023-07-26T15:16:25Z; 2023-05-01 |
| Date created | 2023-05-01 |
Files in this item
This item appears in the following Collection(s)
-
Resource Catalogue [335]
A collection of language resources available for download from the RMA of SADiLaR. The collection mostly consists of resources developed with funding from the Department of Arts and Culture.