Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization
Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization
Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revisit iterative back-translation, a simple yet effective semi-supervised method, to investigate whether and how it can improve compositional generalization. In this …