%0 Conference Proceedings %T Neural Lattice-to-Sequence Models for Uncertain Inputs %A Sperber, Matthias %A Neubig, Graham %A Niehues, Jan %A Waibel, Alex %Y Palmer, Martha %Y Hwa, Rebecca %Y Riedel, Sebastian %S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing %D 2017 %8 September %I Association for Computational Linguistics %C Copenhagen, Denmark %F sperber-etal-2017-neural %X 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. %R 10.18653/v1/D17-1145 %U https://aclanthology.org/D17-1145 %U https://doi.org/10.18653/v1/D17-1145 %P 1380-1389