Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
# Monolingual Dutch Models for Zero-Shot Text CLassification
|
2 |
|
3 |
-
This family of Dutch models were finetuned on combined data from the (translated) snli
|
4 |
|
5 |
## The Models
|
6 |
|
7 |
| Base Model | Huggingface id (fine-tuned) |
|
8 |
|-------------------|---------------------|
|
9 |
| [BERTje](https://huggingface.co/GroNLP/bert-base-dutch-cased) | this model |
|
10 |
-
| [RobBERT V2](http://github.com/iPieter/robbert) | robbert-v2-dutch-snli |
|
11 |
-
| [RobBERTje](https://github.com/iPieter/robbertje) | robbertje-dutch-
|
12 |
|
13 |
|
14 |
|
@@ -19,7 +19,7 @@ While this family of models can be used for evaluating (monolingual) NLI dataset
|
|
19 |
- Premise: The food in this place was horrendous
|
20 |
- Hypothesis: This is a negative review
|
21 |
|
22 |
-
For more information on using Natural Language Inference models for zero-shot text classification, we refer to this
|
23 |
|
24 |
By default, all our models are fully compatible with the Huggingface pipeline for zero-shot classification. They can be downloaded and accessed through the following code:
|
25 |
|
@@ -52,9 +52,9 @@ predictions = classifier(text_piece,
|
|
52 |
|
53 |
| Model | Accuracy [%] | F1 [%] |
|
54 |
|-------------------|--------------------------|--------------|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
|
59 |
|
60 |
|
|
|
1 |
# Monolingual Dutch Models for Zero-Shot Text CLassification
|
2 |
|
3 |
+
This family of Dutch models were finetuned on combined data from the (translated) [snli](https://nlp.stanford.edu/projects/snli/) and [SICK-NL](https://github.com/gijswijnholds/sick_nl) datasets. They are intended to be used in zero-shot classification for Dutch through Huggingface Pipelines.
|
4 |
|
5 |
## The Models
|
6 |
|
7 |
| Base Model | Huggingface id (fine-tuned) |
|
8 |
|-------------------|---------------------|
|
9 |
| [BERTje](https://huggingface.co/GroNLP/bert-base-dutch-cased) | this model |
|
10 |
+
| [RobBERT V2](http://github.com/iPieter/robbert) | robbert-v2-dutch-finetuned-snli |
|
11 |
+
| [RobBERTje](https://github.com/iPieter/robbertje) | robbertje-dutch-finetuned-snli |
|
12 |
|
13 |
|
14 |
|
|
|
19 |
- Premise: The food in this place was horrendous
|
20 |
- Hypothesis: This is a negative review
|
21 |
|
22 |
+
For more information on using Natural Language Inference models for zero-shot text classification, we refer to [this paper](https://arxiv.org/abs/1909.00161).
|
23 |
|
24 |
By default, all our models are fully compatible with the Huggingface pipeline for zero-shot classification. They can be downloaded and accessed through the following code:
|
25 |
|
|
|
52 |
|
53 |
| Model | Accuracy [%] | F1 [%] |
|
54 |
|-------------------|--------------------------|--------------|
|
55 |
+
| bert-base-dutch-cased-finetuned-snli | 86.21 | 86.42 |
|
56 |
+
| robbert-v2-dutch-finetuned-snli | **87.61** | **88.02** |
|
57 |
+
| robbertje-dutch-finetuned-snli | 83.28 | 84.11 |
|
58 |
|
59 |
|
60 |
|