A Survey of Optimization and Compression Techniques for Natural Language Processing Models

Read full text Summarise with VIRAT
Authors: Nathan L. Lam
Cited by: 0
References: 48

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Natural Language Processing models have proven to be incredibly useful, boasting a tremendous number of practical applications spanning nearly all fields of study.The ability of NLP models to understand human language can be applied to a wide range of tasks, from generating medical reports to advanced translation.However, these abilities scale significantly with model size, so smaller models experience an exponential performance falloff when compared to large models.Large Language Models (LLMs) are at the forefront of NLP, and can have up to trillions of parameters.These programs are incredibly resourceintensive in their training and operation, and smaller organizations may be unable to properly utilize the full potential of current NLP technology.This paper aims to provide a survey of techniques that can make high-performance NLP models more accessible, whether it be by increasing the performance of weaker models or compressing larger, high-performance models to have more manageable requirements.

Fields of Study & Subjects

Topic Modeling Advanced Neural Network Applications Natural Language Processing Techniques

Publication details

Journal / source
International journal of high school research
Volume
8
Issue
5
Pages
76–82
Publication date
31 March 2026
Language
EN