@inproceedings{bradbury-socher-2017-towards,
    title = "Towards Neural Machine Translation with Latent Tree Attention",
    author = "Bradbury, James  and
      Socher, Richard",
    editor = "Chang, Kai-Wei  and
      Chang, Ming-Wei  and
      Srikumar, Vivek  and
      Rush, Alexander M.",
    booktitle = "Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-4303/",
    doi = "10.18653/v1/W17-4303",
    pages = "12--16",
    abstract = "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."
}