When using torch, TorchText provides ability to load word embedding from FastText pre-trained corpus. However, I am wondering would the same way can we get subword embedding in cases where out-of-vocabulary issues arise ?
0 Answers
Related
When using torch, TorchText provides ability to load word embedding from FastText pre-trained corpus. However, I am wondering would the same way can we get subword embedding in cases where out-of-vocabulary issues arise ?