Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation

04/29/2020
by   Nithin Holla, et al.
0

Deep learning methods typically rely on large amounts of annotated data and do not generalize well to few-shot learning problems where labeled data is scarce. In contrast to human intelligence, such approaches lack versatility and struggle to learn and adapt quickly to new tasks. Meta-learning addresses this problem by training on a large number of related tasks such that new tasks can be learned quickly using a small number of examples. We propose a meta-learning framework for few-shot word sense disambiguation (WSD), where the goal is to disambiguate unseen words from only a few labeled instances. Meta-learning approaches have so far been typically tested in an N-way, K-shot classification setting where each task has N classes with K examples per class. Owing to its nature, WSD deviates from this controlled setup and requires the models to handle a large number of highly unbalanced classes. We extend several popular meta-learning approaches to this scenario, and analyze their strengths and weaknesses in this new challenging setting.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset