yasa — Yet Another Sentence Aligner

yasa is a program that aligns two translations of a text in order to produce a bi-text.  It handles many file formats and supports personal lexicons.  It also uses highly configurable dynamic programming algorithms to find the optimal alignment.
 
Although good sentence aligners are freely available, our laboratory regularly receives requests from researchers and industries for aligning parallel data. This motivated us to release yet another open-source sentence aligner we wrote nearly 20 years ago. This aligner is simple but it performs surprisingly well and often better than more elaborated ones, and do so very fast, allowing to align very large corpora.

Originally created by Philippe Langlais, it was reimplemented by Alexandre Patry. It was reborn as yasa as part of improvements made during Fethi Lamraoui's masters thesis. An article describing the yasa algorithm is available on our site. Should you use our tool in your research, we would appreciate a citation to this article.
 
The tool (Linux package) is temporarily unavailable for download while we are updating it.
 
It is licensed under the Apache License, Version 2.0.
To build and install it, follow the procedure explained in the INSTALL file.