Arrow Research search

Author name cluster

Antoine Domingues

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
2 author rows

Possible papers

2

NAI Journal 2025 Journal Article

Towards Interpretable Embeddings: Aligning Representations With Semantic Aspects

  • Nitisha Jain
  • Antoine Domingues
  • Adwait Baokar
  • Albert Meroño Peñuela
  • Elena Simperl

Knowledge graph embedding models (KGEMs) project entities and relations from knowledge graphs (KGs) into dense vector spaces, enabling tasks such as link prediction and recommendation systems. However, these embeddings typically suffer from a lack of interpretability and struggle to represent entity similarities in a way that is meaningful to humans. To address these challenges, we introduce InterpretE, a neuro-symbolic approach that generates interpretable vector spaces aligned with human-understandable entity aspects. By explicitly linking entity representations to their desired semantic aspects, InterpretE not only improves interpretability but also enhances the clustering of similar entities based on these aspects. Our experiments demonstrate that InterpretE effectively produces embeddings that are interpretable and improve the evaluation of semantic similarities, making it a valuable tool in explainable AI research by supporting transparent decision-making. By offering insights into how embeddings represent entities, InterpretE enables KGEMs to be used for semantic tasks in a more trustworthy and reliable manner.

Details DOI

NeSy Conference 2024 Conference Paper

Bringing Back Semantics to Knowledge Graph Embeddings: An Interpretability Approach

  • Antoine Domingues
  • Nitisha Jain
  • Albert Meroño-Peñuela
  • Elena Simperl

Abstract Knowledge Graph Embeddings Models project entities and relations from Knowledge Graphs into a vector space. Despite their widespread application, concerns persist about the ability of these models to capture entity similarity effectively. To address this, we introduce InterpretE, a novel neuro-symbolic approach to derive interpretable vector spaces with human-understandable dimensions in terms of the features of the entities. We demonstrate the efficacy of InterpretE in encapsulating desired semantic features, presenting evaluations both in the vector space as well as in terms of semantic similarity measurements.

Details
v2026.09.13