SpanEmo: Casting Multi-label Emotion Classification as Span-prediction
This addresses the problem of overlapping emotions in NLP applications like health and consumer analysis, offering an incremental improvement over independent classification methods.
The paper tackled multi-label emotion classification by proposing SpanEmo, a model that treats it as span-prediction to learn associations between labels and words, and introduced a loss function for co-existing emotions, showing effectiveness on SemEval2018 data across English, Arabic, and Spanish languages.
Emotion recognition (ER) is an important task in Natural Language Processing (NLP), due to its high impact in real-world applications from health and well-being to author profiling, consumer analysis and security. Current approaches to ER, mainly classify emotions independently without considering that emotions can co-exist. Such approaches overlook potential ambiguities, in which multiple emotions overlap. We propose a new model "SpanEmo" casting multi-label emotion classification as span-prediction, which can aid ER models to learn associations between labels and words in a sentence. Furthermore, we introduce a loss function focused on modelling multiple co-existing emotions in the input sentence. Experiments performed on the SemEval2018 multi-label emotion data over three language sets (i.e., English, Arabic and Spanish) demonstrate our method's effectiveness. Finally, we present different analyses that illustrate the benefits of our method in terms of improving the model performance and learning meaningful associations between emotion classes and words in the sentence.