Multifaceted Context Representation using Dual Attention for Ontology Alignment

  title={Multifaceted Context Representation using Dual Attention for Ontology Alignment},
  author={Vivek Iyer and Arvind Agarwal and Harshit Kumar},
Ontology Alignment is an important research problem that finds application in various fields such as data integration, data transfer, data preparation etc. State-of-the-art (SOTA) architectures in Ontology Alignment typically use naive domain-dependent approaches with handcrafted rules and manually assigned values, making them unscalable and inefficient. Deep Learning approaches for ontology alignment use domain-specific architectures that are not only in-extensible to other datasets and… 

Figures and Tables from this paper

VeeAlign: a supervised deep learning approach to ontology alignment
This work proposes a dual-attention based approach that uses a multi-faceted context representation to compute contextualized representations of concepts, which is then used to discover semantically equivalent concepts.


DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors
This work presents a novel entity alignment method which refines pre-trained word vectors aiming at deriving ontological entity descriptions which are tailored to the ontology matching task and presents significant performance improvements over the current state-of-the-art.
Augmenting Ontology Alignment by Semantic Embedding and Distant Supervision
This paper presents a machine learning based extension to traditional ontology alignment systems, using distant supervision for training, ontology embedding and Siamese Neural Networks for incorporating richer semantics.
Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules
An approach that combines a neural embedding model and logic-based modules to accurately divide an input ontology matching task into smaller and more tractable matching (sub)tasks is presented.
Entity Alignment for Knowledge Graphs with Multi-order Convolutional Networks
This paper proposes an end-to-end, unsupervised entity alignment framework for cross-lingual KGs that fuses different types of information in order to fully exploit the richness of KG data and adopts a late-fusion mechanism to combine all the information together.
Relational Reflection Entity Alignment
This paper abstracts existing entity alignment methods into a unified framework, Shape-Builder & Alignment, which not only successfully explains the above phenomena but also derives two key criteria for an ideal transformation operation.
Entity alignment via knowledge embedding and type matching constraints for knowledge graph inference
This work proposes a new EA framework based on knowledge embeddings (KEs) and type matching constraints that significantly improves the accuracy of EA compared with state-of-the-art methods.
A Journey From Simple to Complex Alignment on Real-World Ontologies
  • Lu Zhou
  • Computer Science
  • 2018
This paper focuses on developing potential complex alignment benchmarks from realworld ontologies, and utilizes traditional automated alignment systems to suggest complex correspondences, and plans to achieve the ultimate goal of creating and evaluating the authors' own complex alignment system based on logical RDF data compression.
Ontology Matching Using an Artificial Neural Network to Learn Weights
This paper takes an artificial neural network approach to learning and adjusting the above weights, and thereby support a new ontology matching algorithm, with the purpose to avoid some of the disadvantages in both rule-based and learning-based ontological matching approaches.
Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding
The experimental results on real-world datasets show that this approach significantly outperforms the state-of-the-art embedding approaches for cross-lingual entity alignment and could be complemented with methods based on machine translation.
Ontology alignment in the biomedical domain using entity definitions and context
This work proposes a method for enriching entities in an ontology with external definition and context information, and uses this additional information for ontology alignment, and develops a neural architecture capable of encoding the additional information when available.