PaRTE

该数据集包含了1,126对识别文本蕴含（RTE）的例子，旨在评估模型在面对释义时的鲁棒性。此外，该数据集也用于检验模型预测在经过释义的例子中是否保持一致性。该数据集所针对的任务是识别文本蕴含。

This dataset, containing 1,126 example pairs for the Recognizing Textual Entailment (RTE) task, is designed to evaluate the robustness of models when dealing with paraphrased inputs. Additionally, it can also be utilized to examine whether a model's predictions maintain consistency across paraphrased examples. The core task this dataset targets is Recognizing Textual Entailment (RTE).