Permutation Equivariant Models for Compositional Generalization in Language

International Conference on Learning Representations (ICLR)


Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generalization is required. The main contribution of this paper is to hypothesize that language compositionality is a form of group-equivariance. Based on this hypothesis, we propose a set of tools for constructing equivariant sequence-to-sequence models. Throughout a variety of experiments on the SCAN tasks, we analyze the behavior of existing models under the lens of equivariance, and demonstrate that our equivariant architecture is able to achieve the type compositional generalization required in human language understanding.

Related Publications

All Publications

Human Interpretability Workshop at ICML - April 9, 2021

Investigating Effects of Saturation in Integrated Gradients

Vivek Miglani, Bilal Alsallakh, Narine Kokhlikyan, Orion Reblitz-Richardson

ICASSP - April 8, 2021

Multi-Channel Speech Enhancement Using Graph Neural Networks

Panagiotis Tzirakis, Anurag Kumar, Jacob Donley

JMLR - February 11, 2021

The Decoupled Extended Kalman Filter for Dynamic Exponential-Family Factorization Models

Carlos A. Gómez-Uribe, Brian Karrer

ICSE - March 5, 2021

Testing Web Enabled Simulation at Scale Using Metamorphic Testing

John Ahlgren, Maria Eugenia Berezin, Kinga Bojarczuk, Elena Dulskyte, Inna Dvortsova, Johann George, Natalija Gucevska, Mark Harman, Maria Lomeli, Erik Meijer, Silvia Sapora, Justin Spahr-Summers

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy