|
--- |
|
license: apache-2.0 |
|
language: |
|
- nl |
|
pipeline_tag: text-classification |
|
--- |
|
|
|
Fine-tuned model for detecting instances of offensive language in Dutch tweets. The model has been trained with [DALC v2.0 ](https://github.com/tommasoc80/DALC). |
|
|
|
Offensive language definition is inherited from SemEval 2019 OffensEval: "Posts containing any form of non-acceptable language (profanity) or a targeted offence, |
|
which can be veiled or direct. This includes insults, threats, and posts containing profane language or swear words." ([Zampieri et al., 2019](https://aclanthology.org/N19-1144/)) |
|
|
|
The model achieves the following results on multiple test data: |
|
|
|
- DALC held-out test set: macro F1: 79.93; F1 Offensive: 70.34 |
|
- HateCheck-NL (functional benchmark for hate speech): Accuracy: 61.40; Accuracy non-hateful tests: 47.61 ; Accuracy hateful tests: 68.86 |
|
- OP-NL (dynamic benchmark for offensive language): macro F1: 73.56 |
|
|
|
More details on the training settings and pre-processing are available [here](https://github.com/tommasoc80/DALC) |
|
|
