@InProceedings{sperber-EtAl:2017:EMNLP2017,
  author    = {Sperber, Matthias  and  Neubig, Graham  and  Niehues, Jan  and  Waibel, Alex},
  title     = {Neural Lattice-to-Sequence Models for Uncertain Inputs},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  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.},
  url       = {https://www.aclweb.org/anthology/D17-1145}
}