all AI news
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer. (arXiv:2205.11631v1 [cs.CL])
cs.CL updates on arXiv.org arxiv.org
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
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 complete input token attributions. Our
method, …
arxiv black box machine machine translation neural machine translation transformer translation