RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction

TL;DR

This paper introduces RE-Matching, a fine-grained semantic matching approach for zero-shot relation extraction that decomposes similarity into entity and context scores, improving accuracy and speed.

Contribution

The paper proposes a novel fine-grained matching method with feature distillation for zero-shot relation extraction, explicitly modeling entity and context matching patterns.

Findings

Achieves higher F1 score than state-of-the-art methods.

Inference speed is 10 times faster.

Effectively reduces negative impact of irrelevant features.

Abstract

Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should exactly match their hypernyms in the description, while the irrelevant contexts should be ignored when matching. However, general matching methods lack explicit modeling of the above matching pattern. In this work, we propose a fine-grained semantic matching method tailored for zero-shot relation extraction. Following the above matching pattern, we decompose the sentence-level similarity score into entity and context matching scores. Due to the lack of explicit annotations of the redundant components, we design a feature distillation module to adaptively identify the relation-irrelevant features and reduce their negative impact on context matching. Experimental results show that our method achieves higher matching $F_1$ score and has an inference speed 10 times faster, when compared with the state-of-the-art methods.