This project implements a sentence segmentation approach based on the sentence segmentation theory introduced by Biping Meng and Shujian Huang in the paper of "Segmenting Long Sentence Pairs for Statistical Machine Translation".

Quick guide:

1) How to get code:
bzr branch lp:sentence-segmentation
2) How to run the segmentation:
perl segmentation.pl --conf=CONFIG_FILE
Note: Perl v5.10.0 (or upper) built with multi-thread feature enabled is required.