diff options
| author | Marcin Junczys-Dowmunt <marcinjd@microsoft.com> | 2018-11-26 10:38:51 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2018-11-26 10:38:51 +0300 |
| commit | f3d292740fc7ea19e0a4bc970d66e49ef982a698 (patch) | |
| tree | 9881d42c26effd12aeb2e82129815c0d8c2020b6 | |
| parent | dc285935e12a560a82033873d79445402e2e7ec0 (diff) | |
Update README.md
| -rw-r--r-- | training-basics-sentencepiece/README.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/training-basics-sentencepiece/README.md b/training-basics-sentencepiece/README.md index 0fb6a85..76c547e 100644 --- a/training-basics-sentencepiece/README.md +++ b/training-basics-sentencepiece/README.md @@ -267,7 +267,7 @@ BLEU+case.mixed+lang.ro-en+numrefs.1+smooth.exp+test.wmt16+tok.13a+version.1.2.1 ## Is Normalization Actually Required? We also quickly tested if the normalization of Romanian characters is actually neccessary and if there are other methods -of dealing with the noise. SentencePiece supports a method called subword-regularization ((Kudo 2018)[]) that samples different +of dealing with the noise. SentencePiece supports a method called subword-regularization ([Kudo 2018](https://arxiv.org/abs/1804.10959)) that samples different subword splits at training time; ideally resulting in a more robust translation at inference time. Here's the table: |