Coverage vector

[Waino]

Implement coverage in the attention mechanism, following [1].

[1] Tu, Zhaopeng, et al. "Coverage-based Neural Machine Translation." arXiv preprint arXiv:1601.04811 (2016). http://arxiv.org/pdf/1601.04811

[robertostling]

Perhaps a better (= quicker to implement) start would be to implement the decoding-time coverage normalization method from section 7 of the Google NMT paper. This would only require changing the HNMT code so that it returns attention predictions, and then modifying the beam search code in BNAS to use it.