论文标题
在2020 Semeval-2020任务11：宣传特定训练的伯特的宣传检测
UPB at SemEval-2020 Task 11: Propaganda Detection with Domain-Specific Trained BERT
论文作者
论文摘要
操纵性和误导性新闻已成为某些在线新闻媒体的商品，这些新闻对全球人的心态产生了重大影响。宣传是一种经常采用的操纵方法，其目标是通过传播旨在扭曲或操纵意见的想法来影响读者的目标。本文介绍了我们参与2020年Semeval-2020任务11：新闻文章竞赛中宣传技术的检测。我们的方法考虑了专门针对宣传和超党新闻文章的预训练的BERT模型，使其能够为这两个子任务创建更充分的代表，即宣传跨度识别（SI）和宣传技术分类（TC）。我们提出的系统在子任务SI中获得了46.060％的F1分数，在36个团队中排名第五，子任务为5402％的F1得分为54.302％，在32个团队中排名第19。
Manipulative and misleading news have become a commodity for some online news outlets and these news have gained a significant impact on the global mindset of people. Propaganda is a frequently employed manipulation method having as goal to influence readers by spreading ideas meant to distort or manipulate their opinions. This paper describes our participation in the SemEval-2020, Task 11: Detection of Propaganda Techniques in News Articles competition. Our approach considers specializing a pre-trained BERT model on propagandistic and hyperpartisan news articles, enabling it to create more adequate representations for the two subtasks, namely propaganda Span Identification (SI) and propaganda Technique Classification (TC). Our proposed system achieved a F1-score of 46.060% in subtask SI, ranking 5th in the leaderboard from 36 teams and a micro-averaged F1 score of 54.302% for subtask TC, ranking 19th from 32 teams.
