# SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

arXiv: https://arxiv.org/abs/1604.04835 · HTML: https://mlsanity.com/paper/1604.04835/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2016.

## Built on by (most cited first, 18 of 18)

- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Exploring Large Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2308.13916/) (2023)
- [Learning to Walk with Dual Agents for Knowledge Graph Reasoning](https://mlsanity.com/paper/2112.12876/) (2021)
- [Multi-task Pre-training Language Model for Semantic Network Completion](https://mlsanity.com/paper/2201.04843/) (2022)
- [Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network](https://mlsanity.com/paper/2106.06555/) (2021)
- [Graph-Text Multi-Modal Pre-training for Medical Representation Learning](https://mlsanity.com/paper/2203.09994/) (2022)
- [Augmenting Knowledge Graphs for Better Link Prediction](https://mlsanity.com/paper/2203.13965/) (2022)
- [Large Language Model Enhanced Knowledge Representation Learning: A Survey](https://mlsanity.com/paper/2407.00936/) (2024)
- [A shallow neural model for relation prediction](https://mlsanity.com/paper/2101.09090/) (2021)
- [Automated Feature-Topic Pairing: Aligning Semantic and Embedding Spaces in Spatial Representation Learning](https://mlsanity.com/paper/2109.11053/) (2021)
- [On Event-Driven Knowledge Graph Completion in Digital Factories](https://mlsanity.com/paper/2109.03655/) (2021)
- [Delving Into Deep Walkers: A Convergence Analysis of Random-Walk-Based Vertex Embeddings](https://mlsanity.com/paper/2107.10014/) (2021)
- [VEM2L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion](https://mlsanity.com/paper/2207.01528/) (2022)
- [Neurosymbolic Methods for Rule Mining](https://mlsanity.com/paper/2408.05773/) (2024)
- [Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods](https://mlsanity.com/paper/2506.05626/) (2025)
- [Retrieval of Scientific and Technological Resources for Experts and Scholars](https://mlsanity.com/paper/2204.06142/) (2022)
- [VN Network: Embedding Newly Emerging Entities with Virtual Neighbors](https://mlsanity.com/paper/2402.14033/) (2024)
- [TrendGen: An Outfit Recommendation and Display System](https://mlsanity.com/paper/2603.27264/) (2026)

## Abstract (arXiv)

Knowledge representation is an important, long-history topic in AI, and there have been a large amount of work for knowledge graph embedding which projects symbolic entities and relations into low-dimensional, real-valued vector space. However, most embedding methods merely concentrate on data fitting and ignore the explicit semantic expression, leading to uninterpretable representations. Thus, traditional embedding methods have limited potentials for many applications such as question answering, and entity classification. To this end, this paper proposes a semantic representation method for knowledge graph (KSR), which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple. Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple. Extensive experiments justify our model outperforms other state-of-the-art baselines substantially.