It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (short for abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.
@article{arxiv.1902.07282,
title = {Semantic Neural Machine Translation using AMR},
author = {Linfeng Song and Daniel Gildea and Yue Zhang and Zhiguo Wang and Jinsong Su},
journal= {arXiv preprint arXiv:1902.07282},
year = {2019}
}