diff options
author | Marcin Junczys-Dowmunt <marcinjd@microsoft.com> | 2018-11-26 10:36:58 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2018-11-26 10:36:58 +0300 |
commit | dc285935e12a560a82033873d79445402e2e7ec0 (patch) | |
tree | 77529e6851ad77c239e2a71ed875c466a1cc35cf | |
parent | 1d5df93e22a2dfb58330a98f182cfd4f32825aba (diff) |
Update README.md
-rw-r--r-- | training-basics-sentencepiece/README.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/training-basics-sentencepiece/README.md b/training-basics-sentencepiece/README.md index 0941189..0fb6a85 100644 --- a/training-basics-sentencepiece/README.md +++ b/training-basics-sentencepiece/README.md @@ -279,8 +279,8 @@ Here's the table: | raw+sampling | | | We see that keeping the noise untouched (raw) results indeed in the worst of the three system, normalization (normalized) is best, -closely followed by sampled subwords splits (raw+sampling). This is an interesting result: although normalization is generally better -it is not trivial to discover the problem in the first place. Creating a normalization table is another added difficulty and on top of +closely followed by sampled subwords splits (raw+sampling). This is an interesting result: although normalization is generally better, +it is not trivial to discover the problem in the first place. Creating a normalization table is another added difficulty - and on top of that normalization breaks reversibility. Subword sampling seems to be a viable alternative when dealing with character-level noise with no added complexity compared to raw text. It does however take longer to converge, being a regularization method. |