rsennrich/subword-nmt
1
1
Fork 0
mirror of https://github.com/rsennrich/subword-nmt.git synced 2024-11-27 12:42:07 +03:00
Code Issues Packages Projects Releases Wiki Activity

update reference

Browse Source
This commit is contained in:
Rico Sennrich 2016-06-01 14:49:14 +01:00
parent 5d2d3758ad
commit 3004836285
4 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -29,6 +29,6 @@ PUBLICATIONS
The segmentation methods are described in:
Rico Sennrich, Barry Haddow and Alexandra Birch (2015):
Rico Sennrich, Barry Haddow and Alexandra Birch (2016):
Neural Machine Translation of Rare Words with Subword Units
http://arxiv.org/abs/1508.07909
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016). Berlin, Germany.

3
apply_bpe.py
View File

@ -7,7 +7,8 @@ The text will not be smaller, but use only a fixed vocabulary, with rare words
encoded as variable-length sequences of subword units.
Reference:
Rico Sennrich, Barry Haddow and Alexandra Birch (2015). Neural Machine Translation of Rare Words with Subword Units.
Rico Sennrich, Barry Haddow and Alexandra Birch (2016). Neural Machine Translation of Rare Words with Subword Units.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016). Berlin, Germany.
"""
from __future__ import unicode_literals, division

3
bpe_toy.py
View File

@ -9,7 +9,8 @@ This is an (inefficient) toy implementation that shows the algorithm. For proces
indexing and incremental updates can be used to speed up the implementation (see learn_bpe.py).
Reference:
Rico Sennrich, Barry Haddow and Alexandra Birch (2015). Neural Machine Translation of Rare Words with Subword Units.
Rico Sennrich, Barry Haddow and Alexandra Birch (2016). Neural Machine Translation of Rare Words with Subword Units.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016). Berlin, Germany.
"""

3
learn_bpe.py
View File

@ -7,7 +7,8 @@ Unlike the original BPE, it does not compress the plain text, but can be used to
of a text to a configurable number of symbols, with only a small increase in the number of tokens.
Reference:
Rico Sennrich, Barry Haddow and Alexandra Birch (2015). Neural Machine Translation of Rare Words with Subword Units.
Rico Sennrich, Barry Haddow and Alexandra Birch (2016). Neural Machine Translation of Rare Words with Subword Units.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016). Berlin, Germany.
"""
from __future__ import unicode_literals