Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT
Siyuan Lu, Chenchen Zhou, Keli Xie, Jun Lin, and Zhongfeng Wang

TL;DR
This paper introduces ELBERT, a lightweight BERT variant with a confidence-window-based early exit mechanism, enabling a fast and accurate financial sentiment analysis system that significantly outperforms existing methods in speed and maintains high accuracy.
Contribution
The paper presents ELBERT and a novel acceleration method with an effective early exit mechanism, improving speed and accuracy for BERT-based NLP tasks, especially in financial sentiment analysis.
Findings
Achieves nearly 40x speedup in text processing.
Outperforms FastBERT in speed while maintaining high accuracy.
Provides a practical solution for real-time financial sentiment analysis.
Abstract
With the development of deep learning and Transformer-based pre-trained models like BERT, the accuracy of many NLP tasks has been dramatically improved. However, the large number of parameters and computations also pose challenges for their deployment. For instance, using BERT can improve the predictions in the financial sentiment analysis (FSA) task but slow it down, where speed and accuracy are equally important in terms of profits. To address these issues, we first propose an efficient and lightweight BERT (ELBERT) along with a novel confidence-window-based (CWB) early exit mechanism. Based on ELBERT, an innovative method to accelerate text processing on the GPU platform is developed, solving the difficult problem of making the early exit mechanism work more effectively with a large input batch size. Afterward, a fast and high-accuracy FSA system is built. Experimental results show…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStock Market Forecasting Methods · Machine Learning in Materials Science · Sentiment Analysis and Opinion Mining
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Adam · Weight Decay · Dropout · WordPiece · Attention Dropout · Dense Connections · Linear Warmup With Linear Decay
