Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer. (arXiv:2205.11631v2 [cs.CL] UPDATED)

In Neural Machine Translation (NMT), each token prediction is conditioned on
the source sentence and the target prefix (what has been previously translated
at a decoding step). However, previous work on interpretability in NMT has
mainly focused solely on source sentence tokens' attributions. Therefore, we
lack a full understanding of the influences of every input token (source
sentence and target prefix) in the model predictions. In this work, we propose
an interpretability method that tracks input tokens' attributions for both …

arxiv black box machine machine translation neural machine translation transformer translation