Improving neural machine translation with soft template prediction

Abstract

Although neural machine translation (NMT) has achieved significant progress in recent years, most previous NMT models only depend on the source text to generate translation. Inspired by the success of template-based and syntax-based approaches in other fields, we propose to use extracted templates from tree structures as soft target templates to guide the translation procedure. In order to learn the syntactic structure of the target sentences, we adopt the constituency-based parse tree to generate candidate templates. We incorporate the template information into the encoder-decoder framework to jointly utilize the templates and source text. Experiments show that our model significantly outperforms the baseline models on four benchmarks and demonstrate the effectiveness of soft target templates.