Instructions to use DigitalHungerTM/robbert-2023-dutch-large-finetuned-metaphor-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DigitalHungerTM/robbert-2023-dutch-large-finetuned-metaphor-classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="DigitalHungerTM/robbert-2023-dutch-large-finetuned-metaphor-classification")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("DigitalHungerTM/robbert-2023-dutch-large-finetuned-metaphor-classification") model = AutoModelForSequenceClassification.from_pretrained("DigitalHungerTM/robbert-2023-dutch-large-finetuned-metaphor-classification") - Notebooks
- Google Colab
- Kaggle
RobBERT fine-tuned for metaphor classifcation
Author: Mathijs Afman
This is a repository that hosts the model that I used for my bachelor's thesis about metaphor classification for the Dutch language.
Github Repository
This is a link to the GitHub repository that hosts all other code used in the study. (If the link doesn't work, the URL is: https://github.com/DigitalHungerTM/thesis-bachelor-information-science )
Data
The model is based on robbert-2023-dutch-large model and fine-tuned on data from the Openboek corpus by Andreas van Cranenburgh and Gertjan van Noord. I manually annotated this data with the labels 0, 1 and 2 corresponding to "no metaphor", "type 1 metaphor" and "type 2 metaphor" respectively. The data can be found in the GitHub repository.
- Downloads last month
- 3