arXiv subjects

Abigail Swenor

Publications and source records attributed to Abigail Swenor.

3 recordsLinked to original sources

arXiv2026

Modeling Narrative Structure in Latin Epic Poetry with Automatically Generated Story Grammars

Computational methods for analyzing prose and poetry utilize word embeddings and other abstract representations that sometimes obscure context-rich literary text. Inspired by the psychology of reading, we utilize story structure and elements to simulate human narrative comprehension to produce a more comprehensive representation of literary text. We present a method for automatically generating story grammar labels for input texts as a means of analysis that is interpretable and accessible by humanists and technologists alike. Using a large language model (LLM) pipeline and few-shot learning, we label Latin epic poetry with story element labels and use this output directly to aid an analysis of the story structure and style. Our method guides literary scholars to discover new areas of interest across texts and provides a new feature set for further study for downstream machine learning tasks.

cs.CL↗

arXiv2024

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

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.

cs.CL↗

arXiv2022

Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models

Attacks on deep learning models are often difficult to identify and therefore are difficult to protect against. This problem is exacerbated by the use of public datasets that typically are not manually inspected before use. In this paper, we offer a solution to this vulnerability by using, during testing, random perturbations such as spelling correction if necessary, substitution by random synonym, or simply dropping the word. These perturbations are applied to random words in random sentences to defend NLP models against adversarial attacks. Our Random Perturbations Defense and Increased Randomness Defense methods are successful in returning attacked models to similar accuracy of models before attacks. The original accuracy of the model used in this work is 80% for sentiment classification. After undergoing attacks, the accuracy drops to accuracy between 0% and 44%. After applying our defense methods, the accuracy of the model is returned to the original accuracy within statistical significance.

cs.CL↗