Improving Question Answering over Knowledge Graphs Using Graph Summarization

TL;DR

This paper introduces a novel graph summarization method combining RCNN and GCN to improve question answering over knowledge graphs, especially for questions with uncertain answer counts, outperforming previous GCN-based approaches.

Contribution

The paper proposes a new graph summarization technique using RCNN and GCN that enhances entity embeddings and answer recall in KGQA systems for single-relation questions.

Findings

Significant improvement in answer recall for uncertain answer questions

Better entity embeddings through combined RCNN and GCN approach

Outperforms standard GCN-based methods in experiments

Abstract

Question Answering (QA) systems over Knowledge Graphs (KGs) (KGQA) automatically answer natural language questions using triples contained in a KG. The key idea is to represent questions and entities of a KG as low-dimensional embeddings. Previous KGQAs have attempted to represent entities using Knowledge Graph Embedding (KGE) and Deep Learning (DL) methods. However, KGEs are too shallow to capture the expressive features and DL methods process each triple independently. Recently, Graph Convolutional Network (GCN) has shown to be excellent in providing entity embeddings. However, using GCNs to KGQAs is inefficient because GCNs treat all relations equally when aggregating neighbourhoods. Also, a problem could occur when using previous KGQAs: in most cases, questions often have an uncertain number of answers. To address the above issues, we propose a graph summarization technique using Recurrent Convolutional Neural Network (RCNN) and GCN. The combination of GCN and RCNN ensures that the embeddings are propagated together with the relations relevant to the question, and thus better answers. The proposed graph summarization technique can be used to tackle the issue that KGQAs cannot answer questions with an uncertain number of answers. In this paper, we demonstrated the proposed technique on the most common type of questions, which is single-relation questions. Experiments have demonstrated that the proposed graph summarization technique using RCNN and GCN can provide better results when compared to the GCN. The proposed graph summarization technique significantly improves the recall of actual answers when the questions have an uncertain number of answers.