CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT
This work addresses the problem of computational inefficiency for users of multilingual NLP models, though it appears incremental as it builds on existing distillation methods.
The paper tackles the computational resource barrier for deploying large multilingual BERT models by proposing CAMeMBERT, a knowledge distillation technique that achieves an average accuracy of 60.1% while aiming to reduce time and space complexities.
Large language models having hundreds of millions, and even billions, of parameters have performed extremely well on a variety of natural language processing (NLP) tasks. Their widespread use and adoption, however, is hindered by the lack of availability and portability of sufficiently large computational resources. This paper proposes a knowledge distillation (KD) technique building on the work of LightMBERT, a student model of multilingual BERT (mBERT). By repeatedly distilling mBERT through increasingly compressed toplayer distilled teacher assistant networks, CAMeMBERT aims to improve upon the time and space complexities of mBERT while keeping loss of accuracy beneath an acceptable threshold. At present, CAMeMBERT has an average accuracy of around 60.1%, which is subject to change after future improvements to the hyperparameters used in fine-tuning.