Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language. (arXiv:2210.00482v2 [cs.LG] UPDATED)

Deep learning models struggle with compositional generalization, i.e. the
ability to recognize or generate novel combinations of observed elementary
concepts. In hopes of enabling compositional generalization, various
unsupervised learning algorithms have been proposed with inductive biases that
aim to induce compositional structure in learned representations (e.g.
disentangled representation and emergent language learning). In this work, we
evaluate these unsupervised learning algorithms in terms of how well they
enable compositional generalization. Specifically, our evaluation protocol
focuses on whether or not it …

arxiv language representation representation learning study unsupervised