This paper presents the best-performing approach alias "Adam Smith" for the
SemEval-2023 Task 4: "Identification of Human Values behind Arguments". The
goal of the task was to create systems that automatically identify the values
within textual arguments. We train transformer-based models until they reach
their loss minimum or f1-score maximum. Ensembling the models by selecting one
global decision threshold that maximizes the f1-score leads to the
best-performing system in the competition. Ensembling based on stacking with
logistic regressions shows the best performance on an additional dataset
provided to evaluate the robustness ("Nahj al-Balagha"). Apart from outlining
the submitted system, we demonstrate that the use of the large ensemble model
is not necessary and that the system size can be significantly reduced.

本文介绍了在 SemEval-2023 任务 4（“辩论背后人类价值观的识别”）中表现最好的 “亚当・斯密” 方法，该方法利用基于 transformer 的模型通过 Ensembling，选择全局决策阈值，从而实现在竞赛中获得最佳表现。同时，我们还表明使用大型模型的 Ensembling 是不必要的，系统的规模可以大大减小。