MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer
This work addresses the challenge of enabling NLP applications in low-resource languages through more efficient and portable cross-lingual transfer, representing an incremental improvement with novel architectural components.
The paper tackles the problem of weak cross-lingual transfer performance in low-resource languages with pre-trained multilingual models by proposing MAD-X, an adapter-based framework that learns modular language and task representations, achieving state-of-the-art results on named entity recognition and causal commonsense reasoning across diverse languages.
The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingual transfer. However, due to limited model capacity, their transfer performance is the weakest exactly on such low-resource languages and languages unseen during pre-training. We propose MAD-X, an adapter-based framework that enables high portability and parameter-efficient transfer to arbitrary tasks and languages by learning modular language and task representations. In addition, we introduce a novel invertible adapter architecture and a strong baseline method for adapting a pre-trained multilingual model to a new language. MAD-X outperforms the state of the art in cross-lingual transfer across a representative set of typologically diverse languages on named entity recognition and causal commonsense reasoning, and achieves competitive results on question answering. Our code and adapters are available at AdapterHub.ml