Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space
arXiv:1809.03401
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.
arXiv comment7 pages, accepted at EMNLP2018
References in corpus (6)
- From Frequency to Meaning: Vector Space Models of Semantics
- Complex Embeddings for Simple Link Prediction
- Analogical Inference for Multi-Relational Embeddings
- Measuring Semantic Similarity by Latent Relational Analysis
- Embedding Semantic Relations into Word Representations
- Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations