# Improving Question Answering over Knowledge Graphs Using Graph Summarization

arXiv: https://arxiv.org/abs/2203.13570 · HTML: https://mlsanity.com/paper/2203.13570/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 12 of 12)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation](https://mlsanity.com/paper/2010.05468/) (2020)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [Transferring Cross-domain Knowledge for Video Sign Language Recognition](https://mlsanity.com/paper/2003.03703/) (2020)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [A Survey on Graph Neural Networks for Knowledge Graph Completion](https://mlsanity.com/paper/2007.12374/) (2020)
- [Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction](https://mlsanity.com/paper/2104.13173/) (2021)

## Built on by (most cited first, 6 of 6)

- [Patient-Centric Knowledge Graphs: A Survey of Current Methods, Challenges, and Applications](https://mlsanity.com/paper/2402.12608/) (2024)
- [A Comprehensive Survey on Graph Summarization with Graph Neural Networks](https://mlsanity.com/paper/2302.06114/) (2023)
- [PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding](https://mlsanity.com/paper/2310.12638/) (2023)
- [Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages](https://mlsanity.com/paper/2302.04790/) (2023)
- [Graph-Augmented Relation Extraction Model with LLMs-Generated Support Document](https://mlsanity.com/paper/2410.23452/) (2024)
- [Diversified and Adaptive Negative Sampling on Knowledge Graphs](https://mlsanity.com/paper/2410.07592/) (2024)

## Abstract (arXiv)

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.