A new MIT CSAIL paper presents an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars to improve sequence-to-sequence models’ compositional generalization on diagnostic tasks.

Here is a quick read: MIT Presents New Approach for Sequence-to-Sequence Learning with Latent Neural Grammars.

The paper Sequence-to-Sequence Learning with Latent Neural Grammars is on arXiv.



Source link