Using dependency parsing for few-shot learning in distributional semantics
This work addresses the challenge of learning rare word semantics with limited data, but it appears incremental as it builds on existing dependency-based embeddings and baseline models.
The paper tackled the problem of few-shot learning for rare word meaning by using dependency parsing information, resulting in two enhanced methods that improve upon an additive baseline model.
In this work, we explore the novel idea of employing dependency parsing information in the context of few-shot learning, the task of learning the meaning of a rare word based on a limited amount of context sentences. Firstly, we use dependency-based word embedding models as background spaces for few-shot learning. Secondly, we introduce two few-shot learning methods which enhance the additive baseline model by using dependencies.