Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality

Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models. BPE provides multiple benefits, such as handling the out-of-vocabulary problem and reducing vocabulary sparsity. However, this process is defined from the pre-training data statistics, making the tokenization on different domains susceptible to infrequent spelling sequences (e.g., misspellings as in social media or character-level adversarial attacks). On the other hand, pure character-level models, though robust to misspellings, often lead to unreasonably large sequence lengths and make it harder for the model to learn meaningful contiguous characters. To alleviate these challenges, we propose a character-based subword transformer module (char2subword) that learns the subword embedding table in pre-trained models like BERT. Our char2subword module builds representations from characters out of the subword vocabulary, and it can be used as a drop-in replacement of the subword embedding table. The module is robust to character-level alterations such as misspellings, word inflection, casing, and punctuation. We integrate it further with BERT through pre-training while keeping BERT transformer parameters fixed. We show our method's effectiveness by outperforming a vanilla multilingual BERT on the linguistic code-switching evaluation (LinCE) benchmark.