# Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1607.01426 · HTML: https://mlsanity.com/paper/1607.01426/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2016.

## Built on by (most cited first, 30 of 37)

- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2110.13715/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs](https://mlsanity.com/paper/2206.04798/) (2022)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases](https://mlsanity.com/paper/2303.14617/) (2023)
- [Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2110.13522/) (2021)
- [Complex Logical Reasoning over Knowledge Graphs using Large Language Models](https://mlsanity.com/paper/2305.01157/) (2023)
- [SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs](https://mlsanity.com/paper/2110.14890/) (2021)
- [Neural Methods for Logical Reasoning Over Knowledge Graphs](https://mlsanity.com/paper/2209.14464/) (2022)
- [Hopper: Multi-hop Transformer for Spatiotemporal Reasoning](https://mlsanity.com/paper/2103.10574/) (2021)
- [SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning](https://mlsanity.com/paper/2110.14266/) (2021)
- [Learning Symbolic Rules for Interpretable Deep Reinforcement Learning](https://mlsanity.com/paper/2103.08228/) (2021)
- [Message Intercommunication for Inductive Relation Reasoning](https://mlsanity.com/paper/2305.14074/) (2023)
- [FamilyTool: A Multi-hop Personalized Tool Use Benchmark](https://mlsanity.com/paper/2504.06766/) (2025)
- [Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion](https://mlsanity.com/paper/2105.13074/) (2021)
- [Reasoning over Multi-view Knowledge Graphs](https://mlsanity.com/paper/2209.13702/) (2022)
- [Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis](https://mlsanity.com/paper/2308.07942/) (2023)
- [Reinforcement Learning-based Knowledge Graph Reasoning for Explainable Fact-checking](https://mlsanity.com/paper/2310.07613/) (2023)
- [Knowledge Graph Reasoning with Self-supervised Reinforcement Learning](https://mlsanity.com/paper/2405.13640/) (2024)
- [TransNet: Transfer Knowledge for Few-shot Knowledge Graph Completion](https://mlsanity.com/paper/2504.03720/) (2025)
- [River of No Return: Graph Percolation Embeddings for Efficient Knowledge Graph Reasoning](https://mlsanity.com/paper/2305.09974/) (2023)
- [Efficient Learning of Discrete-Continuous Computation Graphs](https://mlsanity.com/paper/2307.14193/) (2023)
- [Two Training Strategies for Improving Relation Extraction over Universal Graph](https://mlsanity.com/paper/2102.06540/) (2021)
- [ImPaKT: A Dataset for Open-Schema Knowledge Base Construction](https://mlsanity.com/paper/2212.10770/) (2022)
- [A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checking](https://mlsanity.com/paper/2104.13046/) (2021)
- [APPTeK: Agent-Based Predicate Prediction in Temporal Knowledge Graphs](https://mlsanity.com/paper/2110.14284/) (2021)
- [Recent Advances in Automated Question Answering In Biomedical Domain](https://mlsanity.com/paper/2111.05937/) (2021)
- [KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers](https://mlsanity.com/paper/2111.15436/) (2021)

## Abstract (arXiv)

Our goal is to combine the rich multistep inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and relations in text and large-scale knowledge bases (KBs). Neelakantan et al. (2015) use RNNs to compose the distributed semantics of multi-hop paths in KBs; however for multiple reasons, the approach lacks accuracy and practicality. This paper proposes three significant modeling advances: (1) we learn to jointly reason about relations, entities, and entity-types; (2) we use neural attention modeling to incorporate multiple paths; (3) we learn to share strength in a single RNN that represents logical composition across all relations. On a largescale Freebase+ClueWeb prediction task, we achieve 25% error reduction, and a 53% error reduction on sparse relations due to shared strength. On chains of reasoning in WordNet we reduce error in mean quantile by 84% versus previous state-of-the-art. The code and data are available at https://rajarshd.github.io/ChainsofReasoning