Dynamic embedded topic models and change-point detection for exploring literary-historical hypotheses

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sirin, Hale, Lippincott, Tom
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909082788560896
author Sirin, Hale
Lippincott, Tom
author_facet Sirin, Hale
Lippincott, Tom
contents We present a novel combination of dynamic embedded topic models and change-point detection to explore diachronic change of lexical semantic modality in classical and early Christian Latin. We demonstrate several methods for finding and characterizing patterns in the output, and relating them to traditional scholarship in Comparative Literature and Classics. This simple approach to unsupervised models of semantic change can be applied to any suitable corpus, and we conclude with future directions and refinements aiming to allow noisier, less-curated materials to meet that threshold.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13905
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic embedded topic models and change-point detection for exploring literary-historical hypotheses
Sirin, Hale
Lippincott, Tom
Computation and Language
We present a novel combination of dynamic embedded topic models and change-point detection to explore diachronic change of lexical semantic modality in classical and early Christian Latin. We demonstrate several methods for finding and characterizing patterns in the output, and relating them to traditional scholarship in Comparative Literature and Classics. This simple approach to unsupervised models of semantic change can be applied to any suitable corpus, and we conclude with future directions and refinements aiming to allow noisier, less-curated materials to meet that threshold.
title Dynamic embedded topic models and change-point detection for exploring literary-historical hypotheses
topic Computation and Language
url https://arxiv.org/abs/2401.13905