1 code implementation • EMNLP 2021 • Inbar Oren, Jonathan Herzig, Jonathan Berant
We evaluate our approach on a new split of the schema2QA dataset, and show that it leads to dramatic improvements in compositional generalization as well as moderate improvements in the traditional i. i. d setup.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Inbar Oren, Jonathan Herzig, Nitish Gupta, Matt Gardner, Jonathan Berant
Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently.