Cautious Steps towards Hybrid Connectionist Bilingual Phrase 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 a real-world title phrase corpus. 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 statistical approaches to alignment, to the best of our knowledge this is the first hybrid connectionist approach for phrase alignment. 1 Introduction Recently, the field of computational linguistics has seen a remarkable trend for certain tasks. Rather than using traditional linguistic symbolic grammar formalisms new learning approaches have been examined, especially for restricted tasks and domains which may not need a deep structural analysis. Among these alternative approaches are statistical (Che..