rsennrich/subword-nmt
1
1
Fork 0
mirror of https://github.com/rsennrich/subword-nmt.git synced 2024-11-27 02:53:55 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add note about BPE-Dropout during training

Browse Source
This commit is contained in:
Ivan Provilkov 2021-02-15 11:59:34 +03:00 committed by GitHub
parent 234923ed53
commit fa326d431c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -94,6 +94,8 @@ On top of the basic BPE implementation, this repository supports:
Doing this on the training corpus can improve quality of the final system; at test time, use BPE without dropout.
In order to obtain reproducible results, argument `--seed` can be used to set the random seed.
**Note:** In the original paper, the authors used BPE-Dropout on each new batch separately. You can copy the training corpus several times to get similar behavior to obtain multiple segmentations for the same sentence.
- support for glossaries:
use the argument `--glossaries` for `subword-nmt apply-bpe` to provide a list of words and/or regular expressions
that should always be passed to the output without subword segmentation