Modular Representation Underlies Systematic Generalization in Neural Natural Language Inference Models

Geiger Atticus
Geiger Atticus
Potts Christopher
Potts Christopher
Cited by: 0|Bibtex|Views18
Other Links: arxiv.org

Abstract:

In adversarial (challenge) testing, we pose hard generalization tasks in order to gain insights into the solutions found by our models. What properties must a system have in order to succeed at these hard tasks? In this paper, we argue that an essential factor is the ability to form modular representations. Our central contribution is a...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments