DAGN: Discourse-Aware Graph Network for Logical Reasoning

TL;DR

This paper introduces DAGN, a discourse-aware graph network that leverages passage-level discourse structures to improve logical reasoning in question answering tasks, outperforming existing sentence-level approaches.

Contribution

The paper proposes a novel discourse-aware graph network that encodes discourse structures as graphs for enhanced logical reasoning in QA, which is a significant advancement over sentence-level relation models.

Findings

DAGN achieves competitive results on ReClor and LogiQA datasets.

Discourse structure encoding improves logical reasoning accuracy.

The model effectively utilizes passage-level relations for QA.

Abstract

Recent QA with logical reasoning questions requires passage-level relations among the sentences. However, current approaches still focus on sentence-level relations interacting among tokens. In this work, we explore aggregating passage-level clues for solving logical reasoning QA by using discourse-based information. We propose a discourse-aware graph network (DAGN) that reasons relying on the discourse structure of the texts. The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks. Experiments are conducted on two logical reasoning QA datasets, ReClor and LogiQA, and our proposed DAGN achieves competitive results. The source code is available at https://github.com/Eleanor-H/DAGN.