mlsanityData to 7 Oct 2026

Open Knowledge Base Canonicalization with Multi-task Learning

arXiv 2403.14733 ↗First posted 21 Mar 2024cs.AI cs.CL cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 41 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

13 of 41 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  3. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
  4. 2015Holographic Embeddings of Knowledge Graphscited by 181
  5. 2019Collective Entity Alignment via Adaptive Featurescited by 30
  6. 2019CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Informationcited by 28
  7. 2020Degree-Aware Alignment for Entities in Tailcited by 17
  8. 2020Open Knowledge Graphs Canonicalization using Variational Autoencoderscited by 9
  9. 2021Reinforcement Learning based Collective Entity Alignment with Adaptive Featurescited by 7
  10. 2022Multi-View Clustering for Open Knowledge Base Canonicalizationcited by 5
  11. 2022Joint Open Knowledge Base Canonicalization and Linkingcited by 5
  12. 2021Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learningcited by 3
1 more
  1. 2023COMBO: A Complete Benchmark for Open KG Canonicalizationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Open Knowledge Base Canonicalization with Multi-task Unlearning
  2. 2024Pre-training and Diagnosing Knowledge Base Completion Models
  3. 2024Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction
  4. 2024Efficient Knowledge Infusion via KG-LLM Alignment
  5. 2025Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling
  6. 2026RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion
  7. 2022Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings
  8. 2024Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective