# Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks

arXiv: https://arxiv.org/abs/1712.01969 · HTML: https://mlsanity.com/paper/1712.01969/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2017.

## Built on by (most cited first, 12 of 12)

- [Knowledge Base Question Answering by Case-based Reasoning over Subgraphs](https://mlsanity.com/paper/2202.10610/) (2022)
- [An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.10368/) (2023)
- [Entity Retrieval for Answering Entity-Centric Questions](https://mlsanity.com/paper/2408.02795/) (2024)
- [Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers](https://mlsanity.com/paper/2103.16289/) (2021)
- [STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation](https://mlsanity.com/paper/2202.07130/) (2022)
- [Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering](https://mlsanity.com/paper/2409.15902/) (2024)
- [An Entity Linking Agent for Question Answering](https://mlsanity.com/paper/2508.03865/) (2025)
- [Incremental Knowledge Based Question Answering](https://mlsanity.com/paper/2101.06938/) (2021)
- [The benefits of query-based KGQA systems for complex and temporal questions in LLM era](https://mlsanity.com/paper/2507.11954/) (2025)
- [Towards Collaborative Question Answering: A Preliminary Study](https://mlsanity.com/paper/2201.09708/) (2022)
- [Prior Bilinear Based Models for Knowledge Graph Completion](https://mlsanity.com/paper/2309.13834/) (2023)
- [Progressive Knowledge Graph Completion](https://mlsanity.com/paper/2404.09897/) (2024)

## Abstract (arXiv)

We examine the problem of question answering over knowledge graphs, focusing on simple questions that can be answered by the lookup of a single fact. Adopting a straightforward decomposition of the problem into entity detection, entity linking, relation prediction, and evidence combination, we explore simple yet strong baselines. On the popular SimpleQuestions dataset, we find that basic LSTMs and GRUs plus a few heuristics yield accuracies that approach the state of the art, and techniques that do not use neural networks also perform reasonably well. These results show that gains from sophisticated deep learning techniques proposed in the literature are quite modest and that some previous models exhibit unnecessary complexity.