Gadi Singer — accepted AI-conference papers

2024

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge

Phillip Howard, Junlin Wang, Vasudev Lal, Gadi Singer, Yejin Choi, Swabha Swayamdipta

NAACL 2024findings

Comparative knowledge (e.g., steel is stronger and heavier than styrofoam) is an essential component of our world knowledge, yet understudied in prior literature. In this paper, we harvest the dramatic improvements in knowledge capabilities of language models into a large-scale comparative knowledge…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2022

NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation

Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, Swabha Swayamdipta

EMNLP 2022finding

While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing approaches for producing counterfactuals, manual or automat…

Cited by 24 Source ↗PDF ↗code ↗Scholar ↗