Open Knowledge Graphs Canonicalization using Variational Autoencoders
This work provides a more efficient and accurate method for canonicalizing entities and relations, which is crucial for improving the quality and usability of open knowledge graphs for researchers and applications relying on structured data.
The paper addresses the issue of uncanonicalized noun and relation phrases in open knowledge graphs, which results in redundant and ambiguous triples. The authors propose CUVA, a joint model that learns embeddings and cluster assignments end-to-end, outperforming existing state-of-the-art approaches on multiple benchmarks.
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.