Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction
This work addresses the problem of computational overhead and annotation burden in zero-shot relation extraction for NLP researchers and practitioners, representing an incremental improvement.
The paper tackles the challenge of predicting unseen relations in zero-shot relation extraction by proposing an efficient multi-grained matching approach that reduces manual annotation costs and balances inference speed with accuracy, achieving state-of-the-art performance.
Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grained matching often requires laborious manual annotation, and rich interactions between instances and label descriptions come with significant computational overhead. In this work, we propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost, and fuses coarse-grained recall and fine-grained classification for rich interactions with guaranteed inference speed. Experimental results show that our approach outperforms the previous State Of The Art (SOTA) methods, and achieves a balance between inference efficiency and prediction accuracy in zero-shot relation extraction tasks. Our code is available at https://github.com/longls777/EMMA.