Predicting the top-level ontological concepts of domain entities using word embeddings, informal definitions, and deep learning

This dataset comprises the two datasets described in the article "Predicting the top-level ontological concepts of domain entities using word embeddings, informal definitions, and deep learning." Each dataset is organized into 3 columns:
Column 1: the Dolce-Lite-Plus class in which the term subsumes
Column 2: the term representing an OntoWordNet concept
Column 3: the informal description of the respective term

From this dataset, as described in the article, it is possible to search for embedding representations of the terms (column 2) in a word embeddings model. Then use a feed-forward neural network and an LSTM neural network to predict the classes of top of domain terms and their informal descriptions.

The source files can be found at https://github.com/BDI-UFRGS/ESWA2021