Visually Grounded Continual Learning of Compositional Semantics
share
Children's language acquisition from the visual world is a real-world example of continual learning from dynamic and evolving environments; yet we lack a realistic setup to study neural networks' capability in human-like language acquisition. In this paper, we propose a realistic setup by simulating children's language acquisition process. We formulate language acquisition as a masked language modeling task where the model visits a stream of data with continuously shifting distribution. Our training and evaluation encode two important challenges in human's language learning, namely the continual learning and the compositionality. We show the performance of existing continual learning algorithms is far from satisfactory. We also study the interactions between memory based continual learning algorithms and compositional generalization and conclude that overcoming overfitting and compositional overfitting may be crucial for a good performance in our problem setup. Our code and data can be found at https://github.com/INK-USC/VG-CCL.
READ FULL TEXT