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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.