# VeeAlign: Multifaceted Context Representation using Dual Attention for Ontology Alignment

arXiv: https://arxiv.org/abs/2102.04081 · HTML: https://mlsanity.com/paper/2102.04081/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 45 references that are in the map.
- First posted on arXiv 8 Feb 2021.

## Builds on (most cited first, 14 of 14)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://mlsanity.com/paper/1907.04307/) (2019)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [Dual Attention Networks for Multimodal Reasoning and Matching](https://mlsanity.com/paper/1611.00471/) (2016)
- [Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation](https://mlsanity.com/paper/1911.08936/) (2019)
- [Relational Reflection Entity Alignment](https://mlsanity.com/paper/2008.07962/) (2020)
- [Visual Pivoting for (Unsupervised) Entity Alignment](https://mlsanity.com/paper/2009.13603/) (2020)
- [Ontology Alignment in the Biomedical Domain Using Entity Definitions and Context](https://mlsanity.com/paper/1806.07976/) (2018)
- [Ontology alignment repair through modularization and confidence-based heuristics](https://mlsanity.com/paper/1307.5322/) (2013)
- [Ontology Matching with Knowledge Rules](https://mlsanity.com/paper/1507.03097/) (2015)
- [Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules](https://mlsanity.com/paper/2003.05370/) (2020)

## Built on by (most cited first, 6 of 6)

- [Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching](https://mlsanity.com/paper/2205.03447/) (2022)
- [Large Language Models as Oracles for Ontology Alignment](https://mlsanity.com/paper/2508.08500/) (2025)
- [MapperGPT: Large Language Models for Linking and Mapping Entities](https://mlsanity.com/paper/2310.03666/) (2023)
- [OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignment](https://mlsanity.com/paper/2408.06310/) (2024)
- [What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?](https://mlsanity.com/paper/2310.07417/) (2023)
- [Integration of Contextual Descriptors in Ontology Alignment for Enrichment of Semantic Correspondence](https://mlsanity.com/paper/2411.19113/) (2024)

## Abstract (arXiv)

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.