Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space

TL;DR

This paper introduces NLRA, a neural model that captures lexical semantic relations in vector space, overcoming data sparsity and improving relational similarity measurement in NLP tasks.

Contribution

The paper presents a novel neural latent relational analysis model that generalizes pattern co-occurrences, addressing data sparseness in pattern-based semantic relation modeling.

Findings

NLRA outperforms previous pattern-based models in relational similarity tasks.

Combining NLRA with vector offset models achieves state-of-the-art performance.

NLRA effectively captures relations even for word pairs that do not co-occur in data.

Abstract

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 lexico-syntactic 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-the-art model that exploits additional semantic relational data.