Function-words Enhanced Attention Networks for Few-Shot Inverse Relation Classification
This work addresses a specific challenge in natural language processing for researchers and practitioners dealing with limited labeled data in relation classification, though it is incremental as it builds on existing meta-learning and attention methods.
The paper tackles the problem of few-shot inverse relation classification, where existing models struggle with limited data, and proposes a function words enhanced attention framework (FAEA) that improves inverse relation accuracy by 14.33% under a 1-shot setting in FewRel1.0.
The relation classification is to identify semantic relations between two entities in a given text. While existing models perform well for classifying inverse relations with large datasets, their performance is significantly reduced for few-shot learning. In this paper, we propose a function words adaptively enhanced attention framework (FAEA) for few-shot inverse relation classification, in which a hybrid attention model is designed to attend class-related function words based on meta-learning. As the involvement of function words brings in significant intra-class redundancy, an adaptive message passing mechanism is introduced to capture and transfer inter-class differences.We mathematically analyze the negative impact of function words from dot-product measurement, which explains why message passing mechanism effectively reduces the impact. Our experimental results show that FAEA outperforms strong baselines, especially the inverse relation accuracy is improved by 14.33% under 1-shot setting in FewRel1.0.