Abstract
Emotion intensity prediction determines the degree or intensity of an emotion that the author intends to express in a text, extending previous categorical approaches to emotion detection. While most previous work on this topic has concentrated on English texts, other languages would also benefit from fine-grained emotion classification, preferably without having to recreate the amount of annotated data available in English in each new language. Consequently, we explore cross-lingual transfer approaches for fine-grained emotion detection in Spanish and Catalan tweets. To this end we annotate a test set of Spanish and Catalan tweets using Best-Worst scaling. We compare four cross-lingual approaches, e.g., machine translation and cross-lingual embedding projection, which have varying requirements for parallel data -- from millions of parallel sentences to completely unsupervised. The results show that on this data, low-resource methods perform surprisingly better than conventional supervised methods, which we explain through an in-depth error analysis. We make the dataset and the code available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2004.04103
