Detecting emotions expressed in text has become critical to a range of fields. In this work, we investigate ways to exploit label correlations in multi-label emotion recognition models to improve emotion detection. First, we develop two modeling approaches to the problem in order to capture word associations of the emotion words themselves, by either including the emotions in the input, or by leveraging Masked Language Modeling (MLM). Second, we integrate pairwise constraints of emotion representations as regularization terms alongside the classification loss of the models. We split these terms into two categories, local and global. The former dynamically change based on the gold labels, while the latter remain static during training. We demonstrate state-of-the-art performance across Spanish, English, and Arabic in SemEval 2018 Task 1 E-c using monolingual BERT-based models. On top of better performance, we also demonstrate improved robustness. Code is available at https://github.com/gchochla/Demux-MEmo.
翻译:在这项工作中,我们研究如何利用多标签情感识别模型中的标签关联来改善情绪检测。首先,我们开发两种模拟方法来捕捉情绪单词本身的文字联系,要么将情感纳入输入中,要么利用蒙面语言建模(MLM)来捕捉。第二,我们将情感表达的双向限制作为正规化术语,同时对模型进行分类损失。我们将这些术语分为两类,即地方和全球性。我们将这些术语分为两类,前者是基于黄金标签的动态变化,而后者则在培训期间保持静态。我们在SemEval 2018任务1 E-c中展示了西班牙语、英语和阿拉伯语的先进表现,使用单语BERT为基础的模型。除了表现更好外,我们还展示了更强的强健性。我们可在 https://github.com/gchchla/Demux-MEmo中查阅代码。</s>