Exploring Vector Spaces for Semantic Relations
Kata G{\'a}bor, Ha{\"\i}fa Zargayouna, Isabelle Tellier, Davide Buscaldi, Thierry Charnois
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words. Using unsupervised methods and just cosine similarity, encouraging results were obtained for analogical similarities. In this paper, we explore the potential of pre-trained word embeddings to identify generic types of semantic relations in an unsupervised experiment. We propose a new relational similarity measure based on the combination of word2vec's CBOW input and output vectors which outperforms concurrent vector representations, when used for unsupervised clustering on SemEval 2010 Relation Classification data.