diff options
author | Marcin Junczys-Dowmunt <marcinjd@microsoft.com> | 2018-11-26 10:43:10 +0300 |
---|---|---|
committer | Marcin Junczys-Dowmunt <marcinjd@microsoft.com> | 2018-11-26 10:43:10 +0300 |
commit | 1b41c24aff90e121ee992f43804495a333f3bb94 (patch) | |
tree | be17275efcaea5955e52d8e656a562d639481375 | |
parent | 1d5df93e22a2dfb58330a98f182cfd4f32825aba (diff) |
update readme
-rw-r--r-- | training-basics-sentencepiece/README.md | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/training-basics-sentencepiece/README.md b/training-basics-sentencepiece/README.md index 0941189..4facab0 100644 --- a/training-basics-sentencepiece/README.md +++ b/training-basics-sentencepiece/README.md @@ -72,11 +72,11 @@ Files and scripts in this folder have been adapted from the Romanian-English sample from https://github.com/rsennrich/wmt16-scripts. We also add the back-translated data from http://data.statmt.org/rsennrich/wmt16_backtranslations/ as desribed in -http://www.aclweb.org/anthology/W16-2323. The resulting system should be -competitive or even slightly better than reported in the Edinburgh WMT2016 -paper. +http://www.aclweb.org/anthology/W16-2323. In our experiments, +we get a single model that is a good deal than the ensemble from + the Edinburgh WMT2016 paper. -Assuming you one GPU, to execute the complete example type: +Assuming one GPU, to execute the complete example type: ``` ./run-me.sh |