Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction

TL;DR

This paper introduces an efficient multi-grained matching method for zero-shot relation extraction that reduces manual annotation and balances inference speed with accuracy, outperforming previous state-of-the-art approaches.

Contribution

It proposes a novel approach combining virtual entity matching with multi-grained fusion to improve zero-shot relation extraction efficiency and effectiveness.

Findings

Outperforms previous SOTA methods in zero-shot relation extraction.

Balances inference speed and prediction accuracy effectively.

Reduces manual annotation costs through virtual entity matching.

Abstract

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.