Building on Huang et al. GlossBERT for Word Sense Disambiguation
This work addresses the problem of disambiguating word meanings in context for natural language processing, but it is incremental as it builds directly on prior research.
The paper tackles Word Sense Disambiguation by replicating and expanding on GlossBERT, achieving competitive results through dataset tweaking, ensemble methods, and model replacements like BART and ALBERT.
We propose to take on the problem ofWord Sense Disambiguation (WSD). In language, words of the same form can take different meanings depending on context. While humans easily infer the meaning or gloss of such words by their context, machines stumble on this task.As such, we intend to replicated and expand upon the results of Huang et al.GlossBERT, a model which they design to disambiguate these words (Huang et al.,2019). Specifically, we propose the following augmentations: data-set tweaking(alpha hyper-parameter), ensemble methods, and replacement of BERT with BART andALBERT. The following GitHub repository contains all code used in this report, which extends on the code made available by Huang et al.