Lon-ea在SemEval-2023任务11中：用于软标签和硬标签预测的激活函数比较
Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
AI总结：
本文研究了在带分歧学习任务中，深度神经网络输出层不同激活函数对软标签和硬标签预测的影响，通过结合基于BERT的模型并引入新的正弦激活函数进行实验对比。
摘要：
我们研究了在“带分歧学习”任务中，深度神经网络模型输出层的不同激活函数对软标签和硬标签预测的影响。该任务的目标是通过预测软标签来量化分歧的程度。为了预测软标签，我们使用基于BERT的预处理器和编码器，并在保持其他参数不变的情况下改变输出层使用的激活函数。随后，软标签被用于硬标签预测。所考虑的激活函数包括sigmoid，以及一种在模型训练后添加的阶跃函数，和本文首次引入的正弦激活函数。
英文摘要：
We study the influence of different activation functions in the output layer of deep neural network models for soft and hard label prediction in the learning with disagreement task. In this task, the goal is to quantify the amount of disagreement via predicting soft labels. To predict the soft labels, we use BERT-based preprocessors and encoders and vary the activation function used in the output layer, while keeping other parameters constant. The soft labels are then used for the hard label prediction. The activation functions considered are sigmoid as well as a step-function that is added to the model post-training and a sinusoidal activation function, which is introduced for the first time in this paper.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
