Style Extraction on Text Embeddings Using VAE and Parallel Dataset

TL;DR

This paper uses a Variational Autoencoder to analyze and differentiate stylistic features across various Bible translations, demonstrating the model's effectiveness in capturing unique textual styles.

Contribution

Introduces a VAE-based approach for stylistic analysis of text embeddings, specifically applied to Bible translations, highlighting its potential for broader stylistic and AI text generation applications.

Findings

VAE effectively distinguishes different Bible translation styles

Each translation shows a unique stylistic distribution

Model has potential for broader stylistic analysis in text data

Abstract

This study investigates the stylistic differences among various Bible translations using a Variational Autoencoder (VAE) model. By embedding textual data into high-dimensional vectors, the study aims to detect and analyze stylistic variations between translations, with a specific focus on distinguishing the American Standard Version (ASV) from other translations. The results demonstrate that each translation exhibits a unique stylistic distribution, which can be effectively identified using the VAE model. These findings suggest that the VAE model is proficient in capturing and differentiating textual styles, although it is primarily optimized for distinguishing a single style. The study highlights the model's potential for broader applications in AI-based text generation and stylistic analysis, while also acknowledging the need for further model refinement to address the complexity of multi-dimensional stylistic relationships. Future research could extend this methodology to other text domains, offering deeper insights into the stylistic features embedded within various types of textual data.