Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning
Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning
Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by learning specialized encodings for each decoding step. We introduce two key modifications to this model which encourage more disentangled representations and improve …