Machine translation needs a large number of parallel sentence pairs to make sure of having a good translation performance. However, the lack of parallel corpus heavily limits machine translation for low-resources language pairs. We propose a novel method that combines the continuous word embeddings with deep learning to obtain parallel sentences. Since parallel sentences are very invaluable for low-resources language pair, we introduce cross-lingual semantic representation to induce bilingual signals. Our experiments show that we can achieve promising results under lacking external resources for low-resource languages. Finally, we construct a state-of-the-art machine translation system in low-resources language pair.
展开▼