Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?

This paper presents a performance study of transformer language models under different hardware configurations and accuracy requirements and derives empirical observations about these resource/accuracy trade-offs. In particular, we study how the most commonly used BERT-based language models (viz., B...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Sarkar, Souvika, Babar, Mohammad Fakhruddin, Md Mahadi Hassan, Monowar Hasan, Shubhra Kanti Karmaker Santu
Format: Article
Language:English
Subjects:
Accuracy
Constraint modelling
Electronic devices
Embedded systems
Task complexity
Tradeoffs
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a performance study of transformer language models under different hardware configurations and accuracy requirements and derives empirical observations about these resource/accuracy trade-offs. In particular, we study how the most commonly used BERT-based language models (viz., BERT, RoBERTa, DistilBERT, and TinyBERT) perform on embedded systems. We tested them on four off-the-shelf embedded platforms (Raspberry Pi, Jetson, UP2, and UDOO) with 2 GB and 4 GB memory (i.e., a total of eight hardware configurations) and four datasets (i.e., HuRIC, GoEmotion, CoNLL, WNUT17) running various NLP tasks. Our study finds that executing complex NLP tasks (such as "sentiment" classification) on embedded systems is feasible even without any GPUs (e.g., Raspberry Pi with 2 GB of RAM). Our findings can help designers understand the deployability and performance of transformer language models, especially those based on BERT architectures.
ISSN:2331-8422
DOI:10.48550/arxiv.2304.11520