Многоязычный трансформер

AbstractWe propose a novel adapter layer formalism for adapting multilingual models. They are more parameter-efficient than existing adapter layers while obtaining as good or better performance. The layers are specific …...

Multilingual Transformer-based language models, usually pretrained on more than 100 languages, have been shown to achieve outstanding results in a wide range of cross- lingual transfer tasks. However, it remains …...

AbstractThe prevalent use of offensive content in social media has become an important reason for concern for online platforms (customer service chat-boxes, social media platforms, etc). Classifying offensive and hate-speech …...