Better Few-Shot Relation Extraction with Label Prompt Dropout
This work addresses the challenge of leveraging textual labels effectively in few-shot learning for relation extraction, offering an incremental improvement over existing methods.
The paper tackled the problem of few-shot relation extraction by proposing label prompt dropout, a method that randomly removes label descriptions during learning to improve class representations, resulting in significantly better performance on the task.
Few-shot relation extraction aims to learn to identify the relation between two entities based on very limited training examples. Recent efforts found that textual labels (i.e., relation names and relation descriptions) could be extremely useful for learning class representations, which will benefit the few-shot learning task. However, what is the best way to leverage such label information in the learning process is an important research question. Existing works largely assume such textual labels are always present during both learning and prediction. In this work, we argue that such approaches may not always lead to optimal results. Instead, we present a novel approach called label prompt dropout, which randomly removes label descriptions in the learning process. Our experiments show that our approach is able to lead to improved class representations, yielding significantly better results on the few-shot relation extraction task.