Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
This addresses the lack of annotated datasets for word sense disambiguation, offering an incremental improvement for natural language processing applications.
The paper tackles the problem of few-shot word sense disambiguation by proposing a model with variational semantic memory, which advances state-of-the-art performance and supports effective learning in data-scarce scenarios like one-shot settings.
A critical challenge faced by supervised word sense disambiguation (WSD) is the lack of large annotated datasets with sufficient coverage of words in their diversity of senses. This inspired recent research on few-shot WSD using meta-learning. While such work has successfully applied meta-learning to learn new word senses from very few examples, its performance still lags behind its fully supervised counterpart. Aiming to further close this gap, we propose a model of semantic memory for WSD in a meta-learning setting. Semantic memory encapsulates prior experiences seen throughout the lifetime of the model, which aids better generalization in limited data settings. Our model is based on hierarchical variational inference and incorporates an adaptive memory update rule via a hypernetwork. We show our model advances the state of the art in few-shot WSD, supports effective learning in extremely data scarce (e.g. one-shot) scenarios and produces meaning prototypes that capture similar senses of distinct words.