A Word Embedding Analysis towards Ontology Enrichment
Mikael Poetsch, Ulisses Brisolara Corrêa, Larissa Astrogildo de Freitas · Research in Computing Science · 2019
Word Embedding is a set of language modeling and feature learning techniques in Natural Language Processing where words or phrases are mapped to vectors of real numbers.This approach could be used in many tasks of Natural Language Processing, such as Text Classification, Part-Of-Speech Tagging, Named Entity Recognition, Sentiment Analysis, and others.In this paper we created different Word Embedding models, using TripAdvisor's hotel reviews.The corpus was pre-processed, in order to reduce noise, and then submitted to four Word Embedding algorithms: Word2Vec, FastText, Wang2Vec, and GloVe.Finally, HOntology concepts and relations are compared with the outputs of models created aiming to improve it, enriching this domain ontology.