A Study on Word Vector Models for Representing Korean Semantic Information

Abstract

This paper examines whether the Global Vector model is applicable to Korean data as a universal learning algorithm. The main purpose of this study is to compare the global vector model (GloVe) with the word2vec models such as a continuous bag-of-words (CBOW) model and a skip-gram (SG) model. For this purpose, we conducted an experiment by employing an evaluation corpus consisting of 70 target words and 819 pairs of Korean words for word similarities and analogies, respectively. Results of the word similarity task indicated that the Pearson correlation coefficients of 0.3133 as compared with the human judgement in GloVe, 0.2637 in CBOW and 0.2177 in SG. The word analogy task showed that the overall accuracy rate of 67% in semantic and syntactic relations was obtained in GloVe, 66% in CBOW and 57% in SG.

A framework for pre-processing of social media feeds based on integrated local knowledge base

“…GloVe is an unsupervised learning algorithm for obtaining word embedding or vector representation of words [81]. The idea is based on obtaining the statistics of word-word co-occurrence from a corpus, which results in representations that showcase interesting linear structures of the word vector space [82].…”