Open Knowledge Graphs Canonicalization using Variational Autoencoders

• Main Authors: Dash, Sarthak, Rossiello, Gaetano, Mihindukulasooriya, Nandana, Bagchi, Sugato, Gliozzo, Alfio
• Format: Journal Article
• Language: English
• Published: 08.12.2020
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computation and Language; Computer Science - Information Retrieval; Computer Science - Learning
• DOI: 10.48550/arxiv.2012.04780

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.