论文标题
SEMEVAL-2020任务的功夫12：基于BERT的多任务学习，用于进攻性语言检测
Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection
论文作者
论文摘要
如今，社交媒体中的进攻内容已成为一个严重的问题，并且自动检测进攻性语言是一项必不可少的任务。在本文中，我们建立了一个进攻性语言检测系统，该系统将多任务学习与基于BERT的模型相结合。使用诸如BERT之类的预训练的语言模型，我们可以有效地学习社交媒体中嘈杂文本的表示形式。此外，为了提高进攻性语言检测的性能，我们利用其他相关任务的监督信号。在2020年攻势比赛中，我们的模型在英语子任务A中获得91.51％的F1得分，这与第一名相当（92.23％的F1）。提供了经验分析来解释我们方法的有效性。
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task. In this paper, we build an offensive language detection system, which combines multi-task learning with BERT-based models. Using a pre-trained language model such as BERT, we can effectively learn the representations for noisy text in social media. Besides, to boost the performance of offensive language detection, we leverage the supervision signals from other related tasks. In the OffensEval-2020 competition, our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place (92.23%F1). An empirical analysis is provided to explain the effectiveness of our approaches.
