@inproceedings{sperber-etal-2017-neural,
    title = "Neural Lattice-to-Sequence Models for Uncertain Inputs",
    author = "Sperber, Matthias  and
      Neubig, Graham  and
      Niehues, Jan  and
      Waibel, Alex",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D17-1145/",
    doi = "10.18653/v1/D17-1145",
    pages = "1380--1389",
    abstract = "The input to a neural sequence-to-sequence model is often determined by an up-stream system, e.g. a word segmenter, part of speech tagger, or speech recognizer. These up-stream models are potentially error-prone. Representing inputs through word lattices allows making this uncertainty explicit by capturing alternative sequences and their posterior probabilities in a compact form. In this work, we extend the TreeLSTM (Tai et al., 2015) into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model. We integrate lattice posterior scores into this architecture by extending the TreeLSTM{'}s child-sum and forget gates and introducing a bias term into the attention mechanism. We experiment with speech translation lattices and report consistent improvements over baselines that translate either the 1-best hypothesis or the lattice without posterior scores."
}