Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space
Koki Washio, Tsuneaki Kato · 2018
Capturing the semantic relations of words in a vector space contributes to many natural language processing tasks.One promising approach exploits lexico-syntactic patterns as features of word pairs.In this paper, we propose a novel model of this pattern-based approach, neural latent relational analysis (NLRA).NLRA can generalize co-occurrences of word pairs and lexicosyntactic patterns, and obtain embeddings of the word pairs that do not co-occur.This overcomes the critical data sparseness problem encountered in previous pattern-based models.Our experimental results on measuring relational similarity demonstrate that NLRA outperforms the previous pattern-based models.In addition, when combined with a vector offset model, NLRA achieves a performance comparable to that of the state-of-theart model that exploits additional semantic relational data.