Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings

@inproceedings{jayawardana2017deriving,
  title={{Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings}},
  author={Jayawardana, Vindula and Lakmal, Dimuthu and de Silva, Nisansa and Perera, Amal Shehan and Sugathadasa, Keet and Ayesha, Buddhi},
  booktitle={2017 Seventh International Conference on Innovative Computing Technology (INTECH)},
  pages={79--84},
  year={2017},
  organization={IEEE},
  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.},
  misc={https://goo.gl/TZPDpr,NLP:ML:ONT:LAW,https://images.deepai.org/publication-preview/deriving-a-representative-vector-for-ontology-classes-with-instance-word-vector-embeddings-page-1-medium.jpg,https://goo.gl/nrh3pn},
  doi={10.1109/intech.2017.8102426}
}