Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bothwell, Stephen, Swenor, Abigail, Chiang, David
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914749353033728
author Bothwell, Stephen
Swenor, Abigail
Chiang, David
author_facet Bothwell, Stephen
Swenor, Abigail
Chiang, David
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07792
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation
Bothwell, Stephen
Swenor, Abigail
Chiang, David
Computation and Language
Machine Learning
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.
title Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2404.07792