Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
This work addresses the challenge of quantifying disagreement in annotation tasks for NLP researchers, but it is incremental as it focuses on a specific model component.
The paper investigated the effect of different activation functions in the output layer of BERT-based models for predicting soft and hard labels in a learning with disagreement task, finding that a novel sinusoidal activation function performed comparably to standard sigmoid and step functions.
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.