Skip to main navigation menu Skip to main content Skip to site footer

Vol. 7 (2019)

TACL approved

Semantic Neural Machine Translation using AMR

Published 2019-04-01

  • Linfeng Song
    • ,
  • Daniel Gildea
    • ,
  • Yue Zhang
    • ,
  • Zhiguo Wang
    • ,
  • Jinsong Su

Linfeng Song
University of Rochester

Daniel Gildea
University of Rochester

Yue Zhang


Zhiguo Wang


Jinsong Su
Xiamen University

Abstract

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 at MIT Press (presented at ACL 2019)