Compositional Language Understanding with Text-based Relational Reasoning
Abstract
Neural networks for natural language reasoning have largely focused on extractive, fact-based question-answering (QA) and common-sense inference. However, it is also crucial to understand the extent to which neural networks can perform relational reasoning and combinatorial generalization from natural language---abilities that are often obscured by annotation artifacts and the dominance of language modeling in standard QA benchmarks. In this work, we present a novel benchmark dataset for language understanding that isolates performance on relational reasoning. We also present a neural message-passing baseline and show that this model, which incorporates a relational inductive bias, is superior at combinatorial generalization compared to a traditional recurrent neural network approach.
Cite
@article{arxiv.1811.02959,
title = {Compositional Language Understanding with Text-based Relational Reasoning},
author = {Koustuv Sinha and Shagun Sodhani and William L. Hamilton and Joelle Pineau},
journal= {arXiv preprint arXiv:1811.02959},
year = {2018}
}
Comments
4 pages of main content, to be presented at Relational Representation Learning Workshop, NIPS 2018, Montreal