language: nl
thumbnail: https://github.com/iPieter/RobBERT/raw/master/res/robbert_logo.png
tags:
- Dutch
- Flemish
- RoBERTa
- RobBERT
license: mit
datasets:
- oscar
- dbrd
- lassy-ud
- europarl-mono
- conll2002
widget:
- text: Hallo, ik ben RobBERT-2022, het nieuwe <mask> taalmodel van de KU Leuven.
RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use.
RobBERT-2022 is the newest release of the Dutch RobBERT model. Since the original release in January 2020, some things happened and our language evolved. For instance, the COVID-19 pandemic introduced a wide range of new words that were suddenly used daily. To account for this and other changes in usage, we release a new Dutch BERT model trained on data from 2022: RobBERT 2022. More in-depth information about RobBERT-2022 can be found in our blog post, our paper and the original RobBERT Github repository.
How to use
RobBERT-2022 and RobBERT both use the RoBERTa architecture and pre-training but with a Dutch tokenizer and training data. RoBERTa is the robustly optimized English BERT model, making it even more powerful than the original BERT model. Given this same architecture, RobBERT can easily be finetuned and inferenced using code to finetune RoBERTa models and most code used for BERT models, e.g. as provided by HuggingFace Transformers library.
By default, RobBERT-2022 has the masked language model head used in training. This can be used as a zero-shot way to fill masks in sentences. It can be tested out for free on RobBERT's Hosted infererence API of Huggingface. You can also create a new prediction head for your own task by using any of HuggingFace's RoBERTa-runners, their fine-tuning notebooks by changing the model name to DTAI-KULeuven/robbert-2022-dutch-base
.
from transformers import AutoTokenizer, AutoForSequenceClassification
tokenizer = RobertaTokenizer.from_pretrained("DTAI-KULeuven/robbert-2022-dutch-base")
model = RobertaForSequenceClassification.from_pretrained("DTAI-KULeuven/robbert-2022-dutch-base")
You can then use most of HuggingFace's BERT-based notebooks for finetuning RobBERT-2022 on your type of Dutch language dataset.
Technical Details From The Paper
Our Performance Evaluation Results
All experiments are described in more detail in our paper, with the code in our GitHub repository.
Sentiment analysis
Predicting whether a review is positive or negative using the Dutch Book Reviews Dataset.
Model | Accuracy [%] |
---|---|
ULMFiT | 93.8 |
BERTje | 93.0 |
RobBERT v2 | 95.1 |
Die/Dat (coreference resolution)
We measured how well the models are able to do coreference resolution by predicting whether "die" or "dat" should be filled into a sentence. For this, we used the EuroParl corpus.
Finetuning on whole dataset
Model | Accuracy [%] | F1 [%] |
---|---|---|
Baseline (LSTM) | 75.03 | |
mBERT | 98.285 | 98.033 |
BERTje | 98.268 | 98.014 |
RobBERT v2 | 99.232 | 99.121 |
Finetuning on 10K examples
We also measured the performance using only 10K training examples. This experiment clearly illustrates that RobBERT outperforms other models when there is little data available.
Model | Accuracy [%] | F1 [%] |
---|---|---|
mBERT | 92.157 | 90.898 |
BERTje | 93.096 | 91.279 |
RobBERT v2 | 97.816 | 97.514 |
Using zero-shot word masking task
Since BERT models are pre-trained using the word masking task, we can use this to predict whether "die" or "dat" is more likely. This experiment shows that RobBERT has internalised more information about Dutch than other models.
Model | Accuracy [%] |
---|---|
ZeroR | 66.70 |
mBERT | 90.21 |
BERTje | 94.94 |
RobBERT v2 | 98.75 |
Part-of-Speech Tagging.
Using the Lassy UD dataset.
Model | Accuracy [%] |
---|---|
Frog | 91.7 |
mBERT | 96.5 |
BERTje | 96.3 |
RobBERT v2 | 96.4 |
Credits and citation
This project is created by Pieter Delobelle, Thomas Winters and Bettina Berendt. If you would like to cite our paper or model, you can use the following BibTeX:
@inproceedings{delobelle2022robbert2022,
doi = {10.48550/ARXIV.2211.08192},
url = {https://arxiv.org/abs/2211.08192},
author = {Delobelle, Pieter and Winters, Thomas and Berendt, Bettina},
keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use},
venue = {arXiv},
year = {2022},
}
@inproceedings{delobelle2020robbert,
title = "{R}ob{BERT}: a {D}utch {R}o{BERT}a-based {L}anguage {M}odel",
author = "Delobelle, Pieter and
Winters, Thomas and
Berendt, Bettina",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.findings-emnlp.292",
doi = "10.18653/v1/2020.findings-emnlp.292",
pages = "3255--3265"
}