Order Embeddings from Merged Ontologies using Sketching
This work provides a computationally efficient way to create order embeddings for researchers and practitioners working with hierarchical data, particularly in specialized domains like medicine, offering an incremental improvement in resource usage.
This paper proposes a low-resource method to generate order embeddings from ontologies, representing hypernymy/hyponymy relations in vector space. The method utilizes countsketch for dimensionality reduction and demonstrates effective merging techniques for medical ontologies and WordNet, yielding accurate representations.
We give a simple, low resource method to produce order embeddings from ontologies. Such embeddings map words to vectors so that order relations on the words, such as hypernymy/hyponymy, are represented in a direct way. Our method uses sketching techniques, in particular countsketch, for dimensionality reduction. We also study methods to merge ontologies, in particular those in medical domains, so that order relations are preserved. We give computational results for medical ontologies and for wordnet, showing that our merging techniques are effective and our embedding yields an accurate representation in both generic and specialised domains.