Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
This work improves few-shot learning for natural language understanding by reducing reliance on redundant or harmful source data, offering a cost-effective solution for domain adaptation.
The paper tackles the problem of few-shot slot tagging by addressing data distribution bias and noise from dissimilar source domains, proposing a similarity-based data selection method and a Shared-Private Network (SP-Net) that outperforms state-of-the-art approaches with fewer source data.
Few-shot slot tagging is an emerging research topic in the field of Natural Language Understanding (NLU). With sufficient annotated data from source domains, the key challenge is how to train and adapt the model to another target domain which only has few labels. Conventional few-shot approaches use all the data from the source domains without considering inter-domain relations and implicitly assume each sample in the domain contributes equally. However, our experiments show that the data distribution bias among different domains will significantly affect the adaption performance. Moreover, transferring knowledge from dissimilar domains will even introduce some extra noises so that affect the performance of models. To tackle this problem, we propose an effective similarity-based method to select data from the source domains. In addition, we propose a Shared-Private Network (SP-Net) for the few-shot slot tagging task. The words from the same class would have some shared features. We extract those shared features from the limited annotated data on the target domain and merge them together as the label embedding to help us predict other unlabelled data on the target domain. The experiment shows that our method outperforms the state-of-the-art approaches with fewer source data. The result also proves that some training data from dissimilar sources are redundant and even negative for the adaption.