Masked ELMo: An evolution of ELMo towards fully contextual RNN language models

This paper presents Masked ELMo, a new RNN-based model for language model pre-training, evolved from the ELMo language model. Contrary to ELMo which only uses independent left-to-right and right-to-left contexts, Masked ELMo learns fully bidirectional word representations. To achieve this, we use the same Masked language model objective as BERT. Additionally, thanks to optimizations on the LSTM neuron, the integration of mask accumulation and bidirectional truncated backpropagation through time, we have increased the training speed of the model substantially. All these improvements make it possible to pre-train a better language model than ELMo while maintaining a low computational cost. We evaluate Masked ELMo by comparing it to ELMo within the same protocol on the GLUE benchmark, where our model outperforms significantly ELMo and is competitive with transformer approaches.