mDAPT: Multilingual Domain Adaptive Pretraining in a Single Model
Rasmus Kær Jørgensen, Mareike Hartmann, Xiang Dai, Desmond Elliott · 2021
Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the domain.Numerous real-world applications are based on domain-specific text, e.g.working with financial or biomedical documents, and these applications often need to support multiple languages.However, largescale domain-specific multilingual pretraining data for such scenarios can be difficult to obtain, due to regulations, legislation, or simply a lack of language-and domain-specific text.One solution is to train a single multilingual model, taking advantage of the data available in as many languages as possible.In this work, we explore the benefits of domain adaptive pretraining with a focus on adapting to multiple languages within a specific domain.We propose different techniques to compose pretraining corpora that enable a language model to both become domain-specific and multilingual.Evaluation on nine domain-specific datasets-for biomedical named entity recognition and financial sentence classificationcovering seven different languages show that a single multilingual domain-specific model can outperform the general multilingual model, and performs close to its monolingual counterpart.This finding holds across two different pretraining methods, adapter-based pretraining and full model pretraining.