Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings
Computation and Language
2019-06-07 v1
Abstract
Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. Traditionally, the mean or median vector is selected. Ontology classes are sets of homogeneous instance objects that can be converted to a vector space by word vector embeddings. This study proposes a methodology to derive a representative vector for ontology classes whose instances were converted to the vector space. We start by deriving five candidate vectors which are then used to train a machine learning model that would calculate a representative vector for the class. We show that our methodology out-performs the traditional mean and median vector representations.
Cite
@article{arxiv.1706.02909,
title = {Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings},
author = {Vindula Jayawardana and Dimuthu Lakmal and Nisansa de Silva and Amal Shehan Perera and Keet Sugathadasa and Buddhi Ayesha},
journal= {arXiv preprint arXiv:1706.02909},
year = {2019}
}