Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction
This work addresses a key challenge in natural language processing for improving semantic understanding, though it appears incremental as it builds on existing embedding methods.
The paper tackles the problem of distinguishing antonyms from synonyms in word embeddings by integrating lexical contrast into vector representations, achieving an average precision of 0.66-0.76 across word classes and outperforming state-of-the-art models on similarity prediction tasks.
We propose a novel vector representation that integrates lexical contrast into distributional vectors and strengthens the most salient features for determining degrees of word similarity. The improved vectors significantly outperform standard models and distinguish antonyms from synonyms with an average precision of 0.66-0.76 across word classes (adjectives, nouns, verbs). Moreover, we integrate the lexical contrast vectors into the objective function of a skip-gram model. The novel embedding outperforms state-of-the-art models on predicting word similarities in SimLex-999, and on distinguishing antonyms from synonyms.