diff options
author | Taku Kudo <taku910@users.noreply.github.com> | 2018-07-12 03:38:11 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2018-07-12 03:38:11 +0300 |
commit | 983c0f5aeb26d6963c3adef94b12e2ea1595dac9 (patch) | |
tree | 4fbfa2bc98d9d93a35449ae83aa40726cd781343 /README.md | |
parent | f949f9e571f824ea7ded63782eef0e3498b1e091 (diff) |
Update README.md
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -18,7 +18,7 @@ with the extension of direct training from raw sentences. SentencePiece allows u ## Technical highlights - **Purely data driven**: SentencePiece trains tokenization and detokenization - models from only raw sentences. No pre-tokenization ([Moses tokenizer](https://github.com/moses-smt/mosesdecoder/blob/master/scripts/tokenizer/tokenizer.perl)/[MeCab](http://taku910.github.io/mecab/)/[KyTea](http://www.phontron.com/kytea/)) is required. + models from from sentences. Pre-tokenization ([Moses tokenizer](https://github.com/moses-smt/mosesdecoder/blob/master/scripts/tokenizer/tokenizer.perl)/[MeCab](http://taku910.github.io/mecab/)/[KyTea](http://www.phontron.com/kytea/)) is not always required. - **Language independent**: SentencePiece treats the sentences just as sequences of Unicode characters. There is no language-dependent logic. - **Multiple subword algorithms**: **BPE** [[Sennrich et al.](http://www.aclweb.org/anthology/P16-1162)] and **unigram language model** [[Kudo.](https://arxiv.org/abs/1804.10959)] are supported. - **Subword regularization**: SentencePiece implements subword sampling for [subword regularization](https://arxiv.org/abs/1804.10959) which helps to improve the robustness and accuracy of NMT models. |