Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation
This work addresses sentiment analysis for Latin language processing, but it is incremental as it builds on existing methods for a specific shared task.
The paper tackled emotion polarity detection in low-resource Latin texts, particularly in rhetorical genres like poetry, by using data augmentation and neural models, achieving the second highest macro-averaged F1 score on the test set.
This paper describes submissions from the team Nostra Domina to the EvaLatin 2024 shared task of emotion polarity detection. Given the low-resource environment of Latin and the complexity of sentiment in rhetorical genres like poetry, we augmented the available data through automatic polarity annotation. We present two methods for doing so on the basis of the $k$-means algorithm, and we employ a variety of Latin large language models (LLMs) in a neural architecture to better capture the underlying contextual sentiment representations. Our best approach achieved the second highest macro-averaged Macro-$F_1$ score on the shared task's test set.