This work delved into the realm of automatic text generation, exploring a variety of techniques ranging from traditional deterministic approaches to more modern stochastic methods. Through analysis of greedy search, beam search, top-k sampling, top-p sampling, contrastive searching, and locally typical searching, this work has provided valuable insights into the strengths, weaknesses, and potential applications of each method. Each text-generating method is evaluated using several standard metrics and a comparative study has been made on the performance of the approaches. Finally, some future directions of research in the field of automatic text generation are also identified.
@article{arxiv.2404.01786,
title = {Generative AI-Based Text Generation Methods Using Pre-Trained GPT-2 Model},
author = {Rohit Pandey and Hetvi Waghela and Sneha Rakshit and Aparna Rangari and Anjali Singh and Rahul Kumar and Ratnadeep Ghosal and Jaydip Sen},
journal= {arXiv preprint arXiv:2404.01786},
year = {2024}
}
Comments
This report pertains to the Capstone Project done by Group 5 of the Fall batch of 2023 students at Praxis Tech School, Kolkata, India. The reports consists of 57 pages and it includes 17 figures and 8 tables. This is the preprint which will be submitted to IEEE CONIT 2024 for review