We present EmoCoder, a modular encoder-decoder architecture that generalizes emotion analysis over different tasks (sentence-level, word-level, label-to-label mapping), domains (natural languages and their registers), and label formats (e.g., polarity classes, basic emotions, and affective dimensions). Experiments on 14 datasets indicate that EmoCoder learns an interpretable language-independent representation of emotions, allows seamless absorption of state-of-the-art models, and maintains strong prediction quality, even when tested on unseen combinations of domains and label formats.

翻译：EmoCoder是一个模块化的编码器解码器结构,它概括了对不同任务(指令级别、字级、标签到标签的绘图)、领域(自然语言及其登记)和标签格式(如极分等级、基本情感和情感维度)的情感分析。 对14个数据集的实验表明,EmoCoder学会了一种可解释的、语言独立的情感表达方式,能够无缝吸收最新模型,并保持了很强的预测质量,即使是在对领域和标签格式的无形组合进行测试时也是如此。