# Lifted Rule Injection for Relation Embeddings

arXiv: https://arxiv.org/abs/1606.08359 · HTML: https://mlsanity.com/paper/1606.08359/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2016.

## Built on by (most cited first, 22 of 22)

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [Incorporating Domain Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2103.00180/) (2021)
- [Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases](https://mlsanity.com/paper/2102.11965/) (2021)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [Graph Collaborative Reasoning](https://mlsanity.com/paper/2112.13705/) (2021)
- [GLiREL -- Generalist Model for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2501.03172/) (2025)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Building Intelligent Agents with Neuro-Symbolic Concepts](https://mlsanity.com/paper/2505.06191/) (2025)
- [Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction](https://mlsanity.com/paper/2302.02601/) (2023)
- [A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives](https://mlsanity.com/paper/2503.18213/) (2025)
- [Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction](https://mlsanity.com/paper/2103.11062/) (2021)
- [Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model](https://mlsanity.com/paper/2406.17739/) (2024)
- [Current and Future Challenges in Knowledge Representation and Reasoning](https://mlsanity.com/paper/2308.04161/) (2023)
- [NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning](https://mlsanity.com/paper/2312.09219/) (2023)
- [Resilience in Knowledge Graph Embeddings](https://mlsanity.com/paper/2410.21163/) (2024)
- [Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling](https://mlsanity.com/paper/2103.06198/) (2021)
- [SentEmojiBot: Empathising Conversations Generation with Emojis](https://mlsanity.com/paper/2105.12399/) (2021)
- [A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2107.10295/) (2021)
- [Exploring Wasserstein Distance across Concept Embeddings for Ontology Matching](https://mlsanity.com/paper/2207.11324/) (2022)
- [Simple Rule Injection for ComplEx Embeddings](https://mlsanity.com/paper/2308.03269/) (2023)
- [EM-NeSy: Expectation Maximization for Neurosymbolic Learning](https://mlsanity.com/paper/2606.14463/) (2026)

## Abstract (arXiv)

Methods based on representation learning currently hold the state-of-the-art in many natural language processing and knowledge base inference tasks. Yet, a major challenge is how to efficiently incorporate commonsense knowledge into such models. A recent approach regularizes relation and entity representations by propositionalization of first-order logic rules. However, propositionalization does not scale beyond domains with only few entities and rules. In this paper we present a highly efficient method for incorporating implication rules into distributed representations for automated knowledge base construction. We map entity-tuple embeddings into an approximately Boolean space and encourage a partial ordering over relation embeddings based on implication rules mined from WordNet. Surprisingly, we find that the strong restriction of the entity-tuple embedding space does not hurt the expressiveness of the model and even acts as a regularizer that improves generalization. By incorporating few commonsense rules, we achieve an increase of 2 percentage points mean average precision over a matrix factorization baseline, while observing a negligible increase in runtime.