Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple.
Our model completes block manipulation tasks with synthetic commands 530 more often than a UNet-based baseline, and learns to localize actions correctly while creating a mapping of symbols to perceptual input that supports compositional reasoning.
Our experiments show CCO substantially boosts the performance of neural symbolic methods on real images.
While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other.
We introduce a novel paraphrastic augmentation strategy based on sentence-level lexically constrained paraphrasing and discriminative span alignment.
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores.
1 code implementation • • Aaron Steven White, Elias Stengel-Eskin, Siddharth Vashishtha, Venkata Govindarajan, Dee Ann Reisinger, Tim Vieira, Keisuke Sakaguchi, Sheng Zhang, Francis Ferraro, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme
We present the Universal Decompositional Semantics (UDS) dataset (v1. 0), which is bundled with the Decomp toolkit (v0. 1).
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model.