SpanEmo: Casting Multi-label Emotion Classification as Span-prediction

TL;DR

SpanEmo introduces a span-prediction approach for multi-label emotion classification, enabling models to better capture overlapping emotions and their associations with words, demonstrated through experiments on multilingual datasets.

Contribution

The paper proposes a novel span-prediction model for multi-label emotion recognition that models co-existing emotions and their word associations, improving over traditional independent classification methods.

Findings

Effective on multilingual datasets (English, Arabic, Spanish).

Improves model performance in recognizing overlapping emotions.

Learns meaningful associations between emotions and words.

Abstract

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.