相关论文: Efficient pre-training objectives for Transformers

In this paper, we study trade-offs between efficiency, cost and accuracy when pre-training Transformer encoders with different pre-training objectives. For this purpose, we analyze features of common objectives and combine them to create…

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…

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to…

ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model.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…

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…

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…

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

The training of Transformer models has revolutionized natural language processing and computer vision, but it remains a resource-intensive and time-consuming process. This paper investigates the applicability of the early-bird ticket…

ELECTRA pretrains a discriminator to detect replaced tokens, where the replacements are sampled from a generator trained with masked language modeling. Despite the compelling performance, ELECTRA suffers from the following two issues.…

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…

The computation necessary for training Transformer-based language models has skyrocketed in recent years. This trend has motivated research on efficient training algorithms designed to improve training, validation, and downstream…

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…

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is…

Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…

Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. The reason is that the model may not learn to pay attention to…

Transformers-based pretrained language models achieve outstanding results in many well-known NLU benchmarks. However, while pretraining methods are very convenient, they are expensive in terms of time and resources. This calls for a study…

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we…

Pretrained transformer-encoder models like DeBERTaV3 and ModernBERT introduce architectural advancements aimed at improving efficiency and performance. Although the authors of ModernBERT report improved performance over DeBERTaV3 on several…