NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
arXiv:2111.04130
Abstract
Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale pretraining. Given some labeled task data and a large general corpus, TLM uses task data as queries to retrieve a tiny subset of the general corpus and jointly optimizes the task objective and the language modeling objective from scratch. On eight classification datasets in four domains, TLM achieves results better than or similar to pretrained language models (e.g., RoBERTa-Large) while reducing the training FLOPs by two orders of magnitude. With high accuracy and efficiency, we hope TLM will contribute to democratizing NLP and expediting its development.
14 pages, 5 figures
References in corpus (6)
- Language Models are Few-Shot Learners
- MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
- Finetuned Language Models Are Zero-Shot Learners
- Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
- Optimal Subarchitecture Extraction For BERT
- Primer: Searching for Efficient Transformers for Language Modeling