AMI @ EVALITA2020: Automatic Misogyny Identification

AMI @ EVALITA2020: Automatic Misogyny Identification
复制标题

AMI @ EVALITA2020:自动厌女症识别

DOI:
--
复制
发表时间:
2020
期刊:
International Workshop on Evaluation of Natural Language and Speech Tools for Italian
影响因子:
--
通讯作者:
Paolo Rosso
Paolo Rosso
中科院分区:
--
文献类型:
--
作者:
E. Fersini;Debora Nozza;Paolo Rosso

文献摘要

被引文献

相似文献

英语。自动厌女症识别fi阳离子是在Evalita2020评估活动中提出的一项共同任务。基于意大利语tweet的AMI子任务被组织成两个子任务:(1)关于厌女症和攻击性的fi阳离子的子任务A;(2)关于模型公平性的子任务B。在评估阶段结束时,我们收到了8个团队提交的20个子任务A和11个子任务B的运行。在本文中,我们概述了AMI共享任务、数据集、评估方法论、参与者所取得的结果以及团队所采用的方法论的讨论。最后,我们得出了一些结论,并讨论了下一步的工作。
English. Automatic Misogyny Identification (AMI) is a shared task proposed at the Evalita 2020 evaluation campaign. The AMI challenge, based on Italian tweets, is organized into two subtasks: (1) Subtask A about misogyny and aggressiveness identification and (2) Subtask B about the fairness of the model. At the end of the evaluation phase, we received a total of 20 runs for Subtask A and 11 runs for Subtask B, submitted by 8 teams. In this paper, we present an overview of the AMI shared task, the datasets, the evaluation method-ology, the results obtained by the participants and a discussion about the method-ology adopted by the teams. Finally, we draw some conclusions and discuss future work.