Китайско-Английский набор данных

We introduce an agreement-based ap- proach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asym- metric latent-variable translation models (i.e., source-to-target and …...

While end-to-end neural machine transla- tion (NMT) has made remarkable progress recently, NMT systems only rely on par- allel corpora for parameter estimation. Since parallel corpora are usually limited in …...

AbstractAlthough neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization …...

AbstractWhile many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we …...