Relation extraction task aims at detecting the semantic relation between a pair of entities in a given target sentence. However, previous methods lack the description of the relation definition, thus needing to model the implication of relations during training. To tackle this issue, we propose a natural language inference method for relation extraction. Given a premise and a hypothesis, the natural language inference task refers to predicting whether the facts in the premise necessarily imply the facts in the hypothesis. Specifically, for each relation type, we construct a relation description. These relation descriptions are the definition of relation, containing prior knowledge that helps model understand the meaning of relation. The given target sentence is viewed as the premise, and these descriptions are viewed as the hypotheses. Then model infers whether these hypotheses can be concluded from the premise. Based on the inference results, our model selects the relation corresponding to the most confident hypothesis as the prediction. Substantial experiments on SemEval2010 Task8 dataset demonstrate that the proposed method achieves state-of-the-art performance.

关系提取任务旨在检测给定目标句子中一对实体之间的语义关系。然而，以前的方法缺乏对关系定义的描述，因此需要在训练过程中对关系的含义进行建模。为了解决这个问题，我们提出了一种用于关系提取的自然语言推理方法。给定一个前提和一个假设，自然语言推理任务是指预测前提中的事实是否必然暗示假设中的事实。具体来说，对于每种关系类型，我们构造一个关系描述。这些关系描述是关系的定义，包含有助于模型理解关系含义的先验知识。给定的目标句子被视为前提，这些描述被视为假设。然后模型推断这些假设是否可以从前提得出。根据推理结果，我们的模型选择与最可信假设对应的关系作为预测。在 SemEval2010 Task8 数据集上的大量实验表明，所提出的方法达到了最先进的性能。