# Open Knowledge Base Canonicalization with Multi-task Learning

arXiv: https://arxiv.org/abs/2403.14733 · HTML: https://mlsanity.com/paper/2403.14733/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 41 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Holographic Embeddings of Knowledge Graphs](https://mlsanity.com/paper/1510.04935/) (2015)
- [Collective Entity Alignment via Adaptive Features](https://mlsanity.com/paper/1912.08404/) (2019)
- [CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information](https://mlsanity.com/paper/1902.00172/) (2019)
- [Degree-Aware Alignment for Entities in Tail](https://mlsanity.com/paper/2005.12132/) (2020)
- [Open Knowledge Graphs Canonicalization using Variational Autoencoders](https://mlsanity.com/paper/2012.04780/) (2020)
- [Reinforcement Learning based Collective Entity Alignment with Adaptive Features](https://mlsanity.com/paper/2101.01353/) (2021)
- [Multi-View Clustering for Open Knowledge Base Canonicalization](https://mlsanity.com/paper/2206.11130/) (2022)
- [Joint Open Knowledge Base Canonicalization and Linking](https://mlsanity.com/paper/2212.01207/) (2022)
- [Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning](https://mlsanity.com/paper/2111.06103/) (2021)
- [COMBO: A Complete Benchmark for Open KG Canonicalization](https://mlsanity.com/paper/2302.03905/) (2023)

## Abstract (arXiv)

The construction of large open knowledge bases (OKBs) is integral to many knowledge-driven applications on the world wide web such as web search. However, noun phrases and relational phrases in OKBs often suffer from redundancy and ambiguity, which calls for the investigation on OKB canonicalization. Current solutions address OKB canonicalization by devising advanced clustering algorithms and using knowledge graph embedding (KGE) to further facilitate the canonicalization process. Nevertheless, these works fail to fully exploit the synergy between clustering and KGE learning, and the methods designed for these subtasks are sub-optimal. To this end, we put forward a multi-task learning framework, namely MulCanon, to tackle OKB canonicalization. In addition, diffusion model is used in the soft clustering process to improve the noun phrase representations with neighboring information, which can lead to more accurate representations. MulCanon unifies the learning objectives of these sub-tasks, and adopts a two-stage multi-task learning paradigm for training. A thorough experimental study on popular OKB canonicalization benchmarks validates that MulCanon can achieve competitive canonicalization results.