Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph

TL;DR

This paper introduces GRF, a method that enhances language generation by enabling multi-hop reasoning over commonsense knowledge graphs, leading to improved performance on reasoning-dependent text generation tasks.

Contribution

It proposes a dynamic multi-hop reasoning flow that leverages the structure of knowledge graphs, advancing beyond simple triple transfer methods for better commonsense-aware generation.

Findings

Outperforms baselines on three reasoning-dependent tasks

Demonstrates effective multi-hop reasoning paths for generation

Provides rationale through inferred reasoning paths

Abstract

Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation. Existing approaches that integrate commonsense knowledge into generative pre-trained language models simply transfer relational knowledge by post-training on individual knowledge triples while ignoring rich connections within the knowledge graph. We argue that exploiting both the structural and semantic information of the knowledge graph facilitates commonsense-aware text generation. In this paper, we propose Generation with Multi-Hop Reasoning Flow (GRF) that enables pre-trained models with dynamic multi-hop reasoning on multi-relational paths extracted from the external commonsense knowledge graph. We empirically show that our model outperforms existing baselines on three text generation tasks that require reasoning over commonsense knowledge. We also demonstrate the effectiveness of the dynamic multi-hop reasoning module with reasoning paths inferred by the model that provide rationale to the generation.