增强型Transformer架构用于自然语言处理
Enhanced Transformer Architecture for Natural Language Processing
AI总结：
本文提出一种增强型Transformer架构，通过全层归一化、加权残差连接、强化学习位置编码和零掩码自注意力，在Multi30k数据集上BLEU分数较原始Transformer提高202.96%。
摘要：
Transformer是自然语言处理（NLP）领域中的一种最先进模型。当前的NLP模型主要通过增加Transformer的数量来提升处理性能。然而，这种技术需要大量的训练资源，例如计算能力。本文提出了一种新颖的Transformer结构。其特点包括全层归一化、加权残差连接、利用强化学习的 positional encoding（位置编码）以及零掩码自注意力。所提出的Transformer模型，称为增强型Transformer，通过使用Multi30k翻译数据集获得的 BLEU（双语评估替补）分数进行了验证。结果表明，与原始Transformer相比，增强型Transformer在翻译数据集上的BLEU分数提高了202.96%。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
