相关论文: Efficient transfer learning for NLP with ELECTRA

Pre-trained language models in the past years have shown exponential growth in model parameters and compute time. ELECTRA is a novel approach for improving the compute efficiency of pre-trained language models (e.g. BERT) based on masked…

The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…

Recently, for few-shot or even zero-shot learning, the new paradigm "pre-train, prompt, and predict" has achieved remarkable achievements compared with the "pre-train, fine-tune" paradigm. After the success of prompt-based GPT-3, a series…

ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model. Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the…

Pre-trained contextual representations (e.g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks. However, large-scale pre-training is computationally expensive. ELECTRA, an early attempt to accelerate…

Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill…

Recently, the use of pre-trained model to build neural network based on transfer learning methodology is increasingly popular. These pre-trained models present the benefit of using less computing resources to train model with smaller amount…

Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright…

Pre-trained masked language models successfully perform few-shot learning by formulating downstream tasks as text infilling. However, as a strong alternative in full-shot settings, discriminative pre-trained models like ELECTRA do not fit…

Bidirectional transformers excel at sentiment analysis, and Large Language Models (LLM) are effective zero-shot learners. Might they perform better as a team? This paper explores collaborative approaches between ELECTRA and GPT-4o for…

Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate…

We introduce Electric, an energy-based cloze model for representation learning over text. Like BERT, it is a conditional generative model of tokens given their contexts. However, Electric does not use masking or output a full distribution…

In Paper I, the effective one-electron potentials (OEP) method was introduced and demonstrated as an efficient approach to reduce the computational cost of evaluation of the charge-transfer interaction energy within the effective fragment…

Executing machine learning inference tasks on resource-constrained edge devices requires careful hardware-software co-design optimizations. Recent examples have shown how transformer-based deep neural network models such as ALBERT can be…

Recent progress in hardware and methodology for training neural networks has ushered in a new generation of large networks trained on abundant data. These models have obtained notable gains in accuracy across many NLP tasks. However, these…

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…

Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before…

The overwhelming amount of biomedical scientific texts calls for the development of effective language models able to tackle a wide range of biomedical natural language processing (NLP) tasks. The most recent dominant approaches are…

Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain. It is particularly important to neural networks, which are very likely to be overfitting. In some fields like…

Computing effective eigenvalues for neutron transport often requires a fine numerical resolution. The main challenge of such computations is the high memory effort of classical solvers, which limits the accuracy of chosen discretizations.…