IREL at SemEval-2023 Task 11: User Conditioned Modelling for Toxicity Detection in Subjective Tasks
IREL at SemEval-2023 Task 11: User Conditioned Modelling for Toxicity Detection in Subjective Tasks
复制标题
IREL 在 SemEval-2023 任务 11：主观任务中毒性检测的用户条件建模
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Vasudeva Varma
中科院分区：
文献类型：
--
作者：
Ankita Maity;Pavan Kandru;Bhavyajeet Singh;Kancharla Aditya Hari;Vasudeva Varma
本文描述了我们在Semeval-2023任务11中使用分歧（LE-WI-DI）中使用的系统。这是一项主观的任务，因为它涉及检测仇恨言论，厌女症和令人反感的语言。因此，预计注释者之间的分歧。我们试验不同的设置，例如特定于主观任务的损失功能，并包括匿名注释者特定的信息，以帮助我们了解分歧的水平。我们对这些不同建模选择的性能差异进行了深入的分析。我们的系统在HS-BREXIT，ARMIS和MD-ADREEMENT的测试集上达到了0.58、4.01和3.70。我们的代码实施已公开可用。
This paper describes our system used in the SemEval-2023 Task 11 Learning With Disagreements (Le-Wi-Di). This is a subjective task since it deals with detecting hate speech, misogyny and offensive language. Thus, disagreement among annotators is expected. We experiment with different settings like loss functions specific for subjective tasks and include anonymized annotator-specific information to help us understand the level of disagreement. We perform an in-depth analysis of the performance discrepancy of these different modelling choices. Our system achieves a cross-entropy of 0.58, 4.01 and 3.70 on the test sets of HS-Brexit, ArMIS and MD-Agreement, respectively. Our code implementation is publicly available.
SemEval-2023 任务 11：带着分歧学习 (LeWiDi)
DOI：
10.18653/v1/2023.semeval-1.314
发表时间：
2023
期刊：
--
影响因子：
--
作者：
Leonardelli E
通讯作者：
Leonardelli E