%0 Generic %1 devries2019bertje %A de Vries, Wietse %A van Cranenburgh, Andreas %A Bisazza, Arianna %A Caselli, Tommaso %A van Noord, Gertjan %A Nissim, Malvina %D 2019 %K BERT dataset dutch pre-trained %T BERTje: A Dutch BERT Model %U http://arxiv.org/abs/1912.09582 %X The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks. Using the same architecture and parameters, we developed and evaluated a monolingual Dutch BERT model called BERTje. Compared to the multilingual BERT model, which includes Dutch but is only based on Wikipedia text, BERTje is based on a large and diverse dataset of 2.4 billion tokens. BERTje consistently outperforms the equally-sized multilingual BERT model on downstream NLP tasks (part-of-speech tagging, named-entity recognition, semantic role labeling, and sentiment analysis). Our pre-trained Dutch BERT model is made available at https://github.com/wietsedv/bertje.

@misc{devries2019bertje, abstract = {The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks. Using the same architecture and parameters, we developed and evaluated a monolingual Dutch BERT model called BERTje. Compared to the multilingual BERT model, which includes Dutch but is only based on Wikipedia text, BERTje is based on a large and diverse dataset of 2.4 billion tokens. BERTje consistently outperforms the equally-sized multilingual BERT model on downstream NLP tasks (part-of-speech tagging, named-entity recognition, semantic role labeling, and sentiment analysis). Our pre-trained Dutch BERT model is made available at https://github.com/wietsedv/bertje.}, added-at = {2020-11-04T15:18:51.000+0100}, author = {de Vries, Wietse and van Cranenburgh, Andreas and Bisazza, Arianna and Caselli, Tommaso and van Noord, Gertjan and Nissim, Malvina}, biburl = {https://www.bibsonomy.org/bibtex/249f33620332d023adb2054ce477f8496/parismic}, description = {[1912.09582] BERTje: A Dutch BERT Model}, interhash = {5f6dfc693db0faab1a0f5e0a50844878}, intrahash = {49f33620332d023adb2054ce477f8496}, keywords = {BERT dataset dutch pre-trained}, note = {cite arxiv:1912.09582}, timestamp = {2020-11-04T15:18:51.000+0100}, title = {BERTje: A Dutch BERT Model}, url = {http://arxiv.org/abs/1912.09582}, year = 2019 }