Cloning Ideology and Style using Deep Learning

TL;DR

This paper presents a deep learning approach using Bi-LSTM to generate text that mimics an author's ideology and style, enabling the creation of new content on unseen topics while maintaining stylistic consistency.

Contribution

It introduces a novel method for author-specific text generation that incorporates style and ideology, utilizing a pre-trained model to improve coherence and reduce contradictions.

Findings

Achieved a perplexity score of 2.23 during training.

Test dataset perplexity score around 3.

Method effectively captures author style and ideology.

Abstract

Text generation tasks have gotten the attention of researchers in the last few years because of their applications on a large scale.In the past, many researchers focused on task-based text generations.Our research focuses on text generation based on the ideology and style of a specific author, and text generation on a topic that was not written by the same author in the past.Our trained model requires an input prompt containing initial few words of text to produce a few paragraphs of text based on the ideology and style of the author on which the model is trained.Our methodology to accomplish this task is based on Bi-LSTM.The Bi-LSTM model is used to make predictions at the character level, during the training corpus of a specific author is used along with the ground truth corpus.A pre-trained model is used to identify the sentences of ground truth having contradiction with the author's corpus to make our language model inclined.During training, we have achieved a perplexity score of 2.23 at the character level. The experiments show a perplexity score of around 3 over the test dataset.