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.

翻译：语义匹配是零样本关系抽取的主流范式，该方法将给定输入与对应标签描述进行匹配。在匹配过程中，输入中的实体需与其在描述中的上位词精确对齐，同时需忽略无关上下文的影响。然而，通用匹配方法缺乏对这种匹配模式的显式建模。本文提出了一种专用于零样本关系抽取的细粒度语义匹配方法，遵循上述匹配模式，将句子级相似度分解为实体匹配分数与上下文匹配分数。针对冗余成分缺乏显式标注的问题，我们设计了特征蒸馏模块，可自适应识别与关系无关的特征并降低其对上下文匹配的负面影响。实验结果表明，与现有最先进方法相比，本方法在取得更高匹配F1分数的同时，推理速度提升了10倍。