Retrofitting Word Representations for Unsupervised Sense Aware Word Similarities

Coming to its senses: Lessons learned from Approximating Retrofitted BERT representations for Word Sense information

Retrofitting static vector space word representations using external knowledge bases has yielded substantial improvements in their lexical-semantic capacities but is non-trivial to apply to contextual word embeddings (CW…

Low Anisotropy Sense Retrofitting (LASeR) : Towards Isotropic and Sense Enriched Representations

Contextual word representation models have shown massive improvements on a multitude of NLP tasks, yet their word sense disambiguation capabilities remain poorly explained. To address this gap, we assess whether contextu…

Expansional Retrofitting for Word Vector Enrichment

Retrofitting techniques, which inject external resources into word representations, have compensated the weakness of distributed representations in semantic and relational knowledge between words. Implicitly retrofitting…

GenSense: A Generalized Sense Retrofitting Model

With the aid of recently proposed word embedding algorithms, the study of semantic similarity has progressed and advanced rapidly. However, many natural language processing tasks need sense level representation. To addre…

Retrofitting Sense-Specific Word Vectors Using Parallel Text