论文标题
LMVE在2020年Semeval-2020任务4：使用预训练语言模型的常识验证和解释
LMVE at SemEval-2020 Task 4: Commonsense Validation and Explanation using Pretraining Language Model
论文作者
论文摘要
本文介绍了我们提交给Semeval-2020任务4的子任务A和B。对于子任务A，我们使用基于Albert的模型具有改进的输入形式，以从两个陈述候选人中挑选出常识性陈述。对于子任务B，我们使用通过提示句子机制增强的多项选择模型来从给定选项中选择有关陈述为何反对常识的原因。此外，我们提出了在子任务之间进行新颖的转移学习策略，以帮助提高性能。在官方测试集上，我们系统的精度分数为95.6 / 94.9，排名7 $^{th} $ / 2 $^{nd} $在后评估排行榜上。
This paper describes our submission to subtask a and b of SemEval-2020 Task 4. For subtask a, we use a ALBERT based model with improved input form to pick out the common sense statement from two statement candidates. For subtask b, we use a multiple choice model enhanced by hint sentence mechanism to select the reason from given options about why a statement is against common sense. Besides, we propose a novel transfer learning strategy between subtasks which help improve the performance. The accuracy scores of our system are 95.6 / 94.9 on official test set and rank 7$^{th}$ / 2$^{nd}$ on Post-Evaluation leaderboard.
