论文标题
CS-NET在Semeval-2020任务4：Siamese Bert for Comve
CS-NET at SemEval-2020 Task 4: Siamese BERT for ComVE
论文作者
论文摘要
在本文中，我们描述了Semeval 2020任务4的系统，其中涉及区分自然语言陈述，这些语言陈述证实了常识，而这些语言陈述与那些没有。组织者提出了三个子任务 - 首先，在两个句子之间选择一个违反常识的句子。其次，确定陈述没有意义的最关键原因。第三，产生了解释反对常识性陈述的新颖原因。在这三个子任务中，本文报告了子任务A和子任务B的系统描述。本文提出了一个基于用于解决子任务的变压器神经网络体系结构的模型。工作中的新颖性在于建筑设计，该设计处理了从两个句子中矛盾的陈述和同时信息提取的逻辑含义。我们使用变压器的平行实例，该实例负责增强性能。在测试集的子任务中，我们在子任务A中获得了94.8％的准确性，在子任务B中达到了89％。
In this paper, we describe our system for Task 4 of SemEval 2020, which involves differentiating between natural language statements that confirm to common sense and those that do not. The organizers propose three subtasks - first, selecting between two sentences, the one which is against common sense. Second, identifying the most crucial reason why a statement does not make sense. Third, generating novel reasons for explaining the against common sense statement. Out of the three subtasks, this paper reports the system description of subtask A and subtask B. This paper proposes a model based on transformer neural network architecture for addressing the subtasks. The novelty in work lies in the architecture design, which handles the logical implication of contradicting statements and simultaneous information extraction from both sentences. We use a parallel instance of transformers, which is responsible for a boost in the performance. We achieved an accuracy of 94.8% in subtask A and 89% in subtask B on the test set.
