Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank
This addresses the challenge of applying multilingual models to low-resource language varieties, which is incremental as it builds on existing adaptation methods.
The paper tackled the problem of adapting multilingual BERT models to low-resource language varieties with limited data, showing that language-specific pretraining and vocabulary augmentation significantly improved dependency parsing performance, especially for the lowest-resource cases.
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled \emph{and unlabeled} data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, we show that these methods significantly improve performance over baselines, especially in the lowest-resource cases, and demonstrate the importance of the relationship between such models' pretraining data and target language varieties.