MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning

TL;DR

MERIt introduces a self-supervised contrastive learning approach guided by meta-paths to enhance logical reasoning in text, addressing data sparsity and overfitting issues.

Contribution

The paper proposes a novel meta-path guided contrastive learning framework for logical reasoning that leverages unlabeled data and includes counterfactual data augmentation.

Findings

Outperforms state-of-the-art on ReClor and LogiQA benchmarks

Effective in reducing overfitting and improving generalization

Utilizes meta-paths to discover logical structures in text

Abstract

Logical reasoning is of vital importance to natural language understanding. Previous studies either employ graph-based models to incorporate prior knowledge about logical relations, or introduce symbolic logic into neural models through data augmentation. These methods, however, heavily depend on annotated training data, and thus suffer from over-fitting and poor generalization problems due to the dataset sparsity. To address these two problems, in this paper, we propose MERIt, a MEta-path guided contrastive learning method for logical ReasonIng of text, to perform self-supervised pre-training on abundant unlabeled text data. Two novel strategies serve as indispensable components of our method. In particular, a strategy based on meta-path is devised to discover the logical structure in natural texts, followed by a counterfactual data augmentation strategy to eliminate the information shortcut induced by pre-training. The experimental results on two challenging logical reasoning benchmarks, i.e., ReClor and LogiQA, demonstrate that our method outperforms the SOTA baselines with significant improvements.