BPDec: Unveiling the Potential of Masked Language Modeling Decoder in BERT pretraining

TL;DR

This paper introduces BPDec, a novel decoder design for BERT pretraining that improves performance on NLP tasks without increasing fine-tuning costs, by focusing on enhancing the decoder while keeping the encoder unchanged.

Contribution

The paper proposes BPDec, a new method for modeling the decoder in BERT pretraining, which enhances performance without modifying the encoder or increasing fine-tuning costs.

Findings

BPDec significantly improves BERT performance on GLUE and SQuAD tasks.

The approach adds moderate pretraining cost but no extra fine-tuning cost.

Enhanced decoders can be tested post-pretraining for better results.

Abstract

BERT (Bidirectional Encoder Representations from Transformers) has revolutionized the field of natural language processing through its exceptional performance on numerous tasks. Yet, the majority of researchers have mainly concentrated on enhancements related to the model structure, such as relative position embedding and more efficient attention mechanisms. Others have delved into pretraining tricks associated with Masked Language Modeling, including whole word masking. DeBERTa introduced an enhanced decoder adapted for BERT's encoder model for pretraining, proving to be highly effective. We argue that the design and research around enhanced masked language modeling decoders have been underappreciated. In this paper, we propose several designs of enhanced decoders and introduce BPDec (BERT Pretraining Decoder), a novel method for modeling training. Typically, a pretrained BERT model is fine-tuned for specific Natural Language Understanding (NLU) tasks. In our approach, we utilize the original BERT model as the encoder, making only changes to the decoder without altering the encoder. This approach does not necessitate extensive modifications to the encoder architecture and can be seamlessly integrated into existing fine-tuning pipelines and services, offering an efficient and effective enhancement strategy. Compared to other methods, while we also incur a moderate training cost for the decoder during the pretraining process, our approach does not introduce additional training costs during the fine-tuning phase. We test multiple enhanced decoder structures after pretraining and evaluate their performance on the GLUE tasks and SQuAD tasks. Our results demonstrate that BPDec, having only undergone subtle refinements to the model structure during pretraining, significantly enhances model performance without escalating the finetuning cost, inference time and serving budget.