# DOLORES: Deep Contextualized Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/1811.00147 · HTML: https://mlsanity.com/paper/1811.00147/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2018.

## Built on by (most cited first, 11 of 11)

- [Exploring Large Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2308.13916/) (2023)
- [Multi-task Pre-training Language Model for Semantic Network Completion](https://mlsanity.com/paper/2201.04843/) (2022)
- [Joint Language Semantic and Structure Embedding for Knowledge Graph Completion](https://mlsanity.com/paper/2209.08721/) (2022)
- [Large Language Model Enhanced Knowledge Representation Learning: A Survey](https://mlsanity.com/paper/2407.00936/) (2024)
- [Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion](https://mlsanity.com/paper/2105.13074/) (2021)
- [PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2210.13715/) (2022)
- [Knowledge Graph Refinement based on Triplet BERT-Networks](https://mlsanity.com/paper/2211.10460/) (2022)
- [Context-driven Visual Object Recognition based on Knowledge Graphs](https://mlsanity.com/paper/2210.11233/) (2022)
- [ReInform: Selecting paths with reinforcement learning for contextualized link prediction](https://mlsanity.com/paper/2211.10688/) (2022)
- [MUSE: Multi-Knowledge Passing on the Edges, Boosting Knowledge Graph Completion](https://mlsanity.com/paper/2408.05283/) (2024)
- [MUSE: Integrating Multi-Knowledge for Knowledge Graph Completion](https://mlsanity.com/paper/2409.17536/) (2024)

## Abstract (arXiv)

We introduce a new method DOLORES for learning knowledge graph embeddings that effectively captures contextual cues and dependencies among entities and relations. First, we note that short paths on knowledge graphs comprising of chains of entities and relations can encode valuable information regarding their contextual usage. We operationalize this notion by representing knowledge graphs not as a collection of triples but as a collection of entity-relation chains, and learn embeddings for entities and relations using deep neural models that capture such contextual usage. In particular, our model is based on Bi-Directional LSTMs and learn deep representations of entities and relations from constructed entity-relation chains. We show that these representations can very easily be incorporated into existing models to significantly advance the state of the art on several knowledge graph prediction tasks like link prediction, triple classification, and missing relation type prediction (in some cases by at least 9.5%).