# Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering

arXiv: https://arxiv.org/abs/1611.02266 · HTML: https://mlsanity.com/paper/1611.02266/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2016.

## Built on by (most cited first, 7 of 7)

- [Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2406.01145/) (2024)
- [SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.15272/) (2024)
- [Evaluation of Question Answering Systems: Complexity of judging a natural language](https://mlsanity.com/paper/2209.12617/) (2022)
- [Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2108.08297/) (2021)
- [Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond](https://mlsanity.com/paper/2508.07353/) (2025)
- [Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction](https://mlsanity.com/paper/2104.13173/) (2021)
- [Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation](https://mlsanity.com/paper/2609.14528/) (2026)

## Abstract (arXiv)

We propose the Gaussian attention model for content-based neural memory access. With the proposed attention model, a neural network has the additional degree of freedom to control the focus of its attention from a laser sharp attention to a broad attention. It is applicable whenever we can assume that the distance in the latent space reflects some notion of semantics. We use the proposed attention model as a scoring function for the embedding of a knowledge base into a continuous vector space and then train a model that performs question answering about the entities in the knowledge base. The proposed attention model can handle both the propagation of uncertainty when following a series of relations and also the conjunction of conditions in a natural way. On a dataset of soccer players who participated in the FIFA World Cup 2014, we demonstrate that our model can handle both path queries and conjunctive queries well.