Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces EmBolic, a novel hyperbolic deep learning architecture for fine-grained emotion analysis that leverages Poincaré discs to capture hierarchical relationships between words and emotions. The model uses a Busemann energy-based attention mechanism in the hyperbolic disc, where queries are generated from text and keys emerge from these queries. Experiments demonstrate strong generalization and good prediction accuracy, suggesting the benefits of hyperbolic representations for affective computing.
Hyperbolic geometry might be the key to unlocking more nuanced emotion analysis from text, capturing semantic ambiguities that flat Euclidean spaces miss.
We present EmBolic - a novel fully hyperbolic deep learning architecture for fine-grained emotion analysis from textual messages. The underlying idea is that hyperbolic geometry efficiently captures hierarchies between both words and emotions. In our context, these hierarchical relationships arise from semantic ambiguities. EmBolic aims to infer the curvature on the continuous space of emotions, rather than treating them as a categorical set without any metric structure. In the heart of our architecture is the attention mechanism in the hyperbolic disc. The model is trained to generate queries (points in the hyperbolic disc) from textual messages, while keys (points at the boundary) emerge automatically from the generated queries. Predictions are based on the Busemann energy between queries and keys, evaluating how well a certain textual message aligns with the class directions representing emotions. Our experiments demonstrate strong generalization properties and reasonably good prediction accuracy even for small dimensions of the representation space. Overall, this study supports our claim that affective computing is one of the application domains where hyperbolic representations are particularly advantageous.