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

Plan2vec: Unsupervised Representation Learning by Latent Plans

Ge Yang, Amy Zhang, Ari Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra

Learning for Dynamics & Control (L4DC) - June 10, 2020

Objective Mismatch in Model-based Reinforcement Learning

Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra

Learning for Dynamics & Control (L4DC) - June 10, 2020

EGO-TOPO: Environment Affordances from Egocentric Video

Tushar Nagarajan, Yanghao Li, Christoph Feichtenhofer, Kristen Grauman

CVPR - June 14, 2020

Listen to Look: Action Recognition by Previewing Audio

Ruohan Gao, Tae-Hyun Oh, Kristen Grauman, Lorenzo Torresani

CVPR - June 14, 2020

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