RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
This work addresses zero-shot relation extraction for natural language processing, offering an incremental improvement with specific performance gains.
The paper tackles the problem of zero-shot relation extraction by proposing a fine-grained semantic matching method that decomposes similarity into entity and context scores, achieving higher F1 scores and 10x faster inference speed compared to state-of-the-art methods.
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.