GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

TL;DR

GrapeQA enhances commonsense question-answering by augmenting and pruning knowledge graph nodes using language model insights, leading to improved reasoning accuracy across multiple datasets.

Contribution

The paper introduces GrapeQA, a novel method that improves knowledge graph-based QA by augmenting relevant nodes and pruning irrelevant ones using language model features.

Findings

Significant performance improvements on OpenBookQA.

Consistent gains over previous LM + KG methods.

Large improvements specifically on OpenBookQA.

Abstract

Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG). A typical approach collects nodes relevant to the QA pair from a KG to form a Working Graph (WG) followed by reasoning using Graph Neural Networks(GNNs). This faces two major challenges: (i) it is difficult to capture all the information from the QA in the WG, and (ii) the WG contains some irrelevant nodes from the KG. To address these, we propose GrapeQA with two simple improvements on the WG: (i) Prominent Entities for Graph Augmentation identifies relevant text chunks from the QA pair and augments the WG with corresponding latent representations from the LM, and (ii) Context-Aware Node Pruning removes nodes that are less relevant to the QA pair. We evaluate our results on OpenBookQA, CommonsenseQA and MedQA-USMLE and see that GrapeQA shows consistent improvements over its LM + KG predecessor (QA-GNN in particular) and large improvements on OpenBookQA.