Yalign is a tool for extracting parallel sentences from comparable corpora.
Statistical Machine Translation relies on parallel corpora (eg.. europarl) for training translation models. However these corpora are limited and take time to create. Yalign is designed to automate this process by finding sentences that are close translation matches from comparable corpora. This opens up avenues for harvesting parallel corpora from sources like translated documents and the web.
Yalign requires that you install scikit-learn.
After that you can install Yalign from PyPi via pip:
sudo pip install yalign
Firstly we need to download and unpack the english to spanish model.
wget http://yalign.machinalis.com/models/0.1/en-es.tar.gz tar -xvzf en-es.tar.gz
Now we can use the yalign-align script along with the english to spanish model to align two web pages.
yalign-align en-es http://en.wikipedia.org/wiki/Antiparticle http://es.wikipedia.org/wiki/Antipart%C3%ADcula
Yalign is not limited to any one language pair. By creating your own models you can align any two languages.
See yalign in action right here.
- Library Reference
Yalign is a Machinalis project. You can view our other open source contributions here.
The Yalign Team: