While neural machine translation (NMT) has made remarkable progress in recent years, it is hard to interpret its internal workings due to the continuous representations and non-linearity of neural networks. In this work, we propose to use layer-wise relevance propagation (LRP) to compute the contribution of each contextual word to arbitrary hidden states in the attention-based encoderdecoder framework. We show that visualization with LRP helps to interpret the internal workings of NMT and analyze translation errors.
No takes yet. Share an insight, caveat, or question.
Ding et al. (2017) studied this question.