diff options
author | Taku Kudo <taku910@users.noreply.github.com> | 2018-06-29 05:10:39 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2018-06-29 05:10:39 +0300 |
commit | 65cae492a7beb34eb61161047c9f1566a30ec77f (patch) | |
tree | 18f4e5047aea03fbb0cd54830c22166b5ef6e75c /README.md | |
parent | d598296450f092dbbb3f17f793ebc9b9af0e3dee (diff) |
Update README.md
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 2 |
1 files changed, 0 insertions, 2 deletions
@@ -286,7 +286,5 @@ Then segment train/test corpus with ```--vocabulary``` option * [SentencePiece Experiments](doc/experiments.md) * [SentencePieceProcessor C++ API](doc/api.md) * [Use custom text normalization rules](doc/normalization.md) -- **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. * [Use custom symbols](doc/special_symbols.md) * [Segmentation and training algorithms in detail] |