VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment

Vivek Iyer, Arvind Agarwal, Harshit Kumar


Abstract
Ontology Alignment is an important research problem applied to various fields such as data integration, data transfer, data preparation, etc. State-of-the-art (SOTA) Ontology Alignment systems typically use naive domain-dependent approaches with handcrafted rules or domain-specific architectures, making them unscalable and inefficient. In this work, we propose VeeAlign, a Deep Learning based model that uses a novel dual-attention mechanism to compute the contextualized representation of a concept which, in turn, is used to discover alignments. By doing this, not only is our approach able to exploit both syntactic and semantic information encoded in ontologies, it is also, by design, flexible and scalable to different domains with minimal effort. We evaluate our model on four different datasets from different domains and languages, and establish its superiority through these results as well as detailed ablation studies. The code and datasets used are available at https://github.com/Remorax/VeeAlign.
Anthology ID:
2021.emnlp-main.842
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10780–10792
Language:
URL:
https://aclanthology.org/2021.emnlp-main.842
DOI:
10.18653/v1/2021.emnlp-main.842
Bibkey:
Cite (ACL):
Vivek Iyer, Arvind Agarwal, and Harshit Kumar. 2021. VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10780–10792, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment (Iyer et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.842.pdf
Software:
 2021.emnlp-main.842.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.842.mp4
Code
 remorax/veealign