Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B

Given that there is a history of using classical NLP methods for sequence alignment / noisy channel decoding, I would've expected a more extensive discussion of how NNs might be able to overcome limitations of simpler methods.

But it seems the opposite is true--here they're using classical approaches to overcome limitations of their neural approach. The paper concludes by observing the "utmost importance of injecting prior linguistic knowledge" into the model. This "linguistic knowledge" is outlined in Section 3, and basically appears in the model as a regularization term based on a classical noisy channel / word alignment model. These regularization terms basically just encourage the neural network to behave like the classical models. And "neural" approach only performs marginally better than the (Berg-Kilpatrick & Klein 2011) paper they're comparing to, which takes a more classical combinatorial approach.

E.g. at 67% accuracy a translation of Linear A would probably being meaningless

This is a step on that way.