Home > Published Issues > 2022 > Volume 13, No. 2, April 2022 >
JAIT 2022 Vol.13(2): 181-185
doi: 10.12720/jait.13.2.181-185

Increasing Accessibility of Language Models with Multi-stage Information Extraction

Conrad Czejdo and Sambit Bhattacharya
Dept. of Mathematics and Computer Science, Fayetteville State University, Fayetteville, United States

Abstract—The capabilities of Language Models (LMs) have continued to increase in recent years, as have their computational requirements. Widely available APIs have also become available. These APIs present new challenges for ease of gradient based fine-tuning by users, resulting in the use models which may be larger than necessary and more expensive, therefore reducing accessibility. In this paper, we present a new methodology for increasing performance of single-shot LMs by chaining multiple smaller LMs. Additionally, as the derived representation is in plain-text it is readily human interpretable. We show that optimizing the context which leads to this derived representation results in improved performance and reduced cost.
Index Terms—Deep Learning (DL), Natural Language Processing (NLP), Language Models (LM), one-shot learning, API

Cite: Conrad Czejdo and Sambit Bhattacharya, "Increasing Accessibility of Language Models with Multi-stage Information Extraction," Journal of Advances in Information Technology, Vol. 13, No. 2, pp. 181-185, April 2022.
Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.