2012-11-29T10:06:11Z (GMT) by Bartholomäus Wloka Werner Winiwarter
<p>We present a method for improving existing statistical machine trans-<br>lation methods using a knowledge base compiled from a bilingual corpus as well<br>as sequence alignment and pattern matching techniques from the area of machine<br>learning and bioinformatics. An alignment algorithm identifies similar sentences,<br>which are then used to construct a better word order for the translation. Our pre-<br>liminary test results indicate a significant improvement of the translation quality.</p> <p> </p>