Enhanced Transformer Architecture for Natural Language Processing
This addresses the computational efficiency challenge for NLP researchers and practitioners, though it appears incremental as it builds directly on the existing transformer paradigm.
The paper tackles the problem of high training resource requirements in NLP transformer models by proposing an Enhanced Transformer architecture with full layer normalization, weighted residual connections, reinforcement learning-based positional encoding, and zero masked self-attention, achieving a 202.96% higher BLEU score on the Multi30k translation dataset compared to the original transformer.
Transformer is a state-of-the-art model in the field of natural language processing (NLP). Current NLP models primarily increase the number of transformers to improve processing performance. However, this technique requires a lot of training resources such as computing capacity. In this paper, a novel structure of Transformer is proposed. It is featured by full layer normalization, weighted residual connection, positional encoding exploiting reinforcement learning, and zero masked self-attention. The proposed Transformer model, which is called Enhanced Transformer, is validated by the bilingual evaluation understudy (BLEU) score obtained with the Multi30k translation dataset. As a result, the Enhanced Transformer achieves 202.96% higher BLEU score as compared to the original transformer with the translation dataset.