Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention

04/14/2021
by   Leon Bergen, et al.
0

We present a model that jointly learns the denotations of words together with their groundings using a truth-conditional semantics. Our model builds on the neurosymbolic approach of Mao et al. (2019), learning to ground objects in the CLEVR dataset (Johnson et al., 2017) using a novel parallel attention mechanism. The model achieves state of the art performance on visual question answering, learning to detect and ground objects with question performance as the only training signal. We also show that the model is able to learn flexible non-canonical groundings just by adjusting answers to questions in the training set.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset