The valence analysis of speakers' utterances or written posts helps to understand the activation and variations of the emotional state throughout the conversation. More recently, the concept of Emotion Carriers (EC) has been introduced to explain the emotion felt by the speaker and its manifestations. In this work, we investigate the natural inter-dependency of valence and ECs via a multi-task learning approach. We experiment with Pre-trained Language Models (PLM) for single-task, two-step, and joint settings for the valence and EC prediction tasks. We compare and evaluate the performance of generative (GPT-2) and discriminative (BERT) architectures in each setting. We observed that providing the ground truth label of one task improves the prediction performance of the models in the other task. We further observed that the discriminative model achieves the best trade-off of valence and EC prediction tasks in the joint prediction setting. As a result, we attain a single model that performs both tasks, thus, saving computation resources at training and inference times.

翻译：对话中说话者的语句或书面帖子的情感价分析有助于理解情感状态在整个对话过程中的激活与变化。近年来，情感载体（Emotion Carriers, EC）的概念被引入，用以解释说话者所感受到的情感及其表现。在本研究中，我们通过多任务学习方法探究情感价与情感载体之间的自然相互依赖性。我们使用预训练语言模型（Pre-trained Language Models, PLM）在单任务、两步和联合设置下进行情感价与情感载体的预测任务。我们比较并评估了各设置下生成式（GPT-2）与判别式（BERT）架构的性能。观察发现，提供某一任务的真值标签可提升另一任务的模型预测性能。进一步观察表明，在联合预测设置中，判别式模型在情感价与情感载体预测任务间取得了最佳权衡。由此，我们实现了单一模型同时完成两项任务，从而在训练和推理阶段节省了计算资源。