Open Knowledge Graphs Canonicalization using Variational Autoencoders

Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo


Abstract
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 and Side Information (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.
Anthology ID:
2021.emnlp-main.811
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10379–10394
Language:
URL:
https://aclanthology.org/2021.emnlp-main.811
DOI:
10.18653/v1/2021.emnlp-main.811
Bibkey:
Cite (ACL):
Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, and Alfio Gliozzo. 2021. Open Knowledge Graphs Canonicalization using Variational Autoencoders. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10379–10394, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Open Knowledge Graphs Canonicalization using Variational Autoencoders (Dash et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.811.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.811.mp4
Code
 IBM/Open-KG-canonicalization