Towards Neural Machine Translation with Latent Tree Attention

09/06/2017
by   James Bradbury, et al.
0

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a recurrent neural network grammar encoder with a novel attentional RNNG decoder and applying policy gradient reinforcement learning to induce unsupervised tree structures on both the source and target. When trained on character-level datasets with no explicit segmentation or parse annotation, the model learns a plausible segmentation and shallow parse, obtaining performance close to an attentional baseline.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset