Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates https://arxiv.org/pdf/1804.10959.pdf
- Byte-Pair-Encoding (BPE)
- Unigram language model
This page is auto-translated from [/nishio/Subword Regularization](https://scrapbox.io/nishio/Subword Regularization) using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.