# Open Knowledge Graphs Canonicalization using Variational Autoencoders

arXiv: https://arxiv.org/abs/2012.04780 · HTML: https://mlsanity.com/paper/2012.04780/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora](https://mlsanity.com/paper/2505.23628/) (2025)
- [Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge](https://mlsanity.com/paper/2211.10997/) (2022)
- [Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study](https://mlsanity.com/paper/2506.19773/) (2025)
- [Multi-View Clustering for Open Knowledge Base Canonicalization](https://mlsanity.com/paper/2206.11130/) (2022)
- [COMBO: A Complete Benchmark for Open KG Canonicalization](https://mlsanity.com/paper/2302.03905/) (2023)
- [Open Knowledge Base Canonicalization with Multi-task Unlearning](https://mlsanity.com/paper/2310.16419/) (2023)
- [Open Knowledge Base Canonicalization with Multi-task Learning](https://mlsanity.com/paper/2403.14733/) (2024)

## Abstract (arXiv)

Noun phrases and Relation phrases in open knowledge graphs are not canonicalized, leading to an explosion of redundant and ambiguous subject-relation-object triples. Existing approaches to solve this problem take a two-step approach. First, they generate embedding representations for both noun and relation phrases, then a clustering algorithm is used to group them using the embeddings as features. In this work, we propose Canonicalizing Using Variational Autoencoders (CUVA), a joint model to learn both embeddings and cluster assignments in an end-to-end approach, which leads to a better vector representation for the noun and relation phrases. Our evaluation over multiple benchmarks shows that CUVA outperforms the existing state-of-the-art approaches. Moreover, we introduce CanonicNell, a novel dataset to evaluate entity canonicalization systems.