Unsupervised Post-processing of Word Vectors via Conceptor Negation

Understand

Word vectors are at the core of many natural language processing tasks.

• Recently, there has been interest in post-processing word vectors to enrich their semantic information.
• In this paper, we introduce a novel word vector post-processing technique based on matrix conceptors (Jaeger2014), a family of regularized identity maps.
• More concretely, we propose to use conceptors to suppress those latent features of word vectors having high variances.