Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space
This work addresses a critical bottleneck in natural language processing for tasks requiring semantic relation understanding, though it is incremental as it builds on existing pattern-based approaches.
The paper tackles the data sparseness problem in pattern-based models for capturing lexical semantic relations by proposing neural latent relational analysis (NLRA), which generalizes co-occurrences to obtain embeddings for non-co-occurring word pairs and outperforms previous pattern-based models in relational similarity tasks.
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.