Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical use of such models-in all languages except English-very limited. In this paper, we investigate the feasibility of training monolingual Transformer-based language models for other languages, taking French as an example and evaluating our language models on part-of-speech tagging, dependency parsing, named entity recognition and natural language inference tasks. We show that the use of web crawled data is preferable to the use of Wikipedia data. More surprisingly, we show that a relatively small web crawled dataset (4GB) leads to results that are as good as those obtained using larger datasets (130+GB). Our best performing model CamemBERT reaches or improves the state of the art in all four downstream tasks.

This paper describes the Linguistic Annotation Framework under development within ISO TC37 SC4 WG1. The Linguistic Annotation Framework is intended to serve as a basis for harmonizing existing language resources as well as developing new ones.

To cite this version:Chris Armbruster, Laurent Romary. Comparing Repository Types -Challenges and barriers for subject-based repositories, research repositories, national repository systems and institutional repositories in serving scholarly communication.

We use the multilingual OSCAR corpus, extracted from Common Crawl via language classification, filtering and cleaning, to train monolingual contextualized word embeddings (ELMo) for five mid-resource languages. We then compare the performance of OSCARbased and Wikipedia-based ELMo embeddings for these languages on the part-ofspeech tagging and parsing tasks. We show that, despite the noise in the Common-Crawlbased OSCAR data, embeddings trained on OSCAR perform much better than monolingual embeddings trained on Wikipedia. They actually equal or improve the current state of the art in tagging and parsing for all five languages. In particular, they also improve over multilingual Wikipedia-based contextual embeddings (multilingual BERT), which almost always constitutes the previous state of the art, thereby showing that the benefit of a larger, more diverse corpus surpasses the crosslingual benefit of multilingual embedding architectures.