Machine Learning

Towards Neural Machine Translation with Latent Tree Attention

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 1 year, 8 months ago.


  • arXiv
    5 pts

    Towards Neural Machine Translation with Latent Tree Attention

    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.

    Towards Neural Machine Translation with Latent Tree Attention
    by James Bradbury, Richard Socher
    https://arxiv.org/pdf/1709.01915v1.pdf

You must be logged in to reply to this topic.