Saved in:
Bibliographic Details
Main Author: Yinkfu, Ngeyen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.22937
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909626542325760
author Yinkfu, Ngeyen
author_facet Yinkfu, Ngeyen
contents This study presents an efficient transformer-based question-answering (QA) model optimized for deployment on a 13th Gen Intel i7-1355U CPU, using the Stanford Question Answering Dataset (SQuAD) v1.1. Leveraging exploratory data analysis, data augmentation, and fine-tuning of a DistilBERT architecture, the model achieves a validation F1 score of 0.6536 with an average inference time of 0.1208 seconds per question. Compared to a rule-based baseline (F1: 0.3124) and full BERT-based models, our approach offers a favorable trade-off between accuracy and computational efficiency. This makes it well-suited for real-time applications on resource-constrained systems. The study includes systematic evaluation of data augmentation strategies and hyperparameter configurations, providing practical insights into optimizing transformer models for CPU-based inference.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs
Yinkfu, Ngeyen
Computation and Language
This study presents an efficient transformer-based question-answering (QA) model optimized for deployment on a 13th Gen Intel i7-1355U CPU, using the Stanford Question Answering Dataset (SQuAD) v1.1. Leveraging exploratory data analysis, data augmentation, and fine-tuning of a DistilBERT architecture, the model achieves a validation F1 score of 0.6536 with an average inference time of 0.1208 seconds per question. Compared to a rule-based baseline (F1: 0.3124) and full BERT-based models, our approach offers a favorable trade-off between accuracy and computational efficiency. This makes it well-suited for real-time applications on resource-constrained systems. The study includes systematic evaluation of data augmentation strategies and hyperparameter configurations, providing practical insights into optimizing transformer models for CPU-based inference.
title Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs
topic Computation and Language
url https://arxiv.org/abs/2505.22937