Generative AI-Based Text Generation Methods Using Pre-Trained GPT-2 Model
It offers insights into method trade-offs for researchers in natural language processing, but is incremental as it applies existing methods without introducing new ones.
This work analyzed various text generation methods, including greedy search and sampling techniques, using a pre-trained GPT-2 model, and provided a comparative evaluation of their performance with standard metrics.
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.