Initial Results on Hybrid Connectionist Bilingual Alignment

1 We examine phrase alignment in a hybrid connectionist framework. We describe the architecture and the learning algorithm of our approach. Simulations have been carried out to demonstrate the feasibility of this approach using two corpora. Although the results of our approach are still at an early stage, we found that a hybrid approach to phrase alignment has the potential to provide good results using relatively little training data. While there have been a lot of statistic approaches to alignment, to the best of our knowledge this is the rst hybrid connectionist approach for phrase alignment.