PipeNet: Question Answering with Semantic Pruning over Knowledge Graphs

TL;DR

PipeNet introduces a semantic pruning approach to improve the efficiency of question answering over knowledge graphs by reducing the subgraph size while maintaining reasoning quality.

Contribution

The paper proposes a novel grounding-pruning-reasoning pipeline that enhances efficiency in KG-based QA by pruning noisy nodes using semantic scores and reasoning with a GAT-based module.

Findings

Significant reduction in computation cost and memory usage.

Maintains high accuracy in CommonsenseQA and OpenBookQA.

Effective subgraph representation through semantic pruning.

Abstract

It is well acknowledged that incorporating explicit knowledge graphs (KGs) can benefit question answering. Existing approaches typically follow a grounding-reasoning pipeline in which entity nodes are first grounded for the query (question and candidate answers), and then a reasoning module reasons over the matched multi-hop subgraph for answer prediction. Although the pipeline largely alleviates the issue of extracting essential information from giant KGs, efficiency is still an open challenge when scaling up hops in grounding the subgraphs. In this paper, we target at finding semantically related entity nodes in the subgraph to improve the efficiency of graph reasoning with KG. We propose a grounding-pruning-reasoning pipeline to prune noisy nodes, remarkably reducing the computation cost and memory usage while also obtaining decent subgraph representation. In detail, the pruning module first scores concept nodes based on the dependency distance between matched spans and then prunes the nodes according to score ranks. To facilitate the evaluation of pruned subgraphs, we also propose a graph attention network (GAT) based module to reason with the subgraph data. Experimental results on CommonsenseQA and OpenBookQA demonstrate the effectiveness of our method.