In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD optimizes the online inference efficiency for GEC by two innovations: 1) it aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism; 2) it uses a shallow decoder instead of the conventional Transformer architecture with balanced encoder-decoder depth to reduce the computational cost during inference. Experiments in both English and Chinese GEC benchmarks show that aggressive decoding could yield the same predictions as greedy decoding but with a significant speedup for online inference. Its combination with the shallow decoder could offer an even higher online inference speedup over the powerful Transformer baseline without quality loss. Not only does our approach allow a single model to achieve the state-of-the-art results in English GEC benchmarks: 66.4 F0.5 in the CoNLL-14 and 72.9 F0.5 in the BEA-19 test set with an almost 10x online inference speedup over the Transformer-big model, but also it is easily adapted to other languages. Our code is available at https://github.com/AutoTemp/Shallow-Aggressive-Decoding.

中文翻译：

---

具有浅层攻击性解码的瞬时语法错误纠正

在本文中，我们提出了浅层攻击性解码（SAD）来提高 Transformer 的在线推理效率，用于瞬时语法纠错（GEC）。SAD 通过两项创新优化了 GEC 的在线推理效率：1）它积极地并行解码尽可能多的令牌，而不是每一步只解码一个令牌，以提高计算并行性；2) 它使用浅层解码器代替传统的 Transformer 架构，具有平衡的编码器-解码器深度，以降低推理过程中的计算成本。在英语和中文 GEC 基准测试中的实验表明，积极解码可以产生与贪婪解码相同的预测，但在线推理的速度显着提高。它与浅层解码器的结合可以在不损失质量的情况下提供比强大的 Transformer 基线更高的在线推理加速。我们的方法不仅允许单个模型在英语 GEC 基准测试中达到最先进的结果：CoNLL-14 中的 66.4 F0.5 和 BEA-19 测试集中的 72.9 F0.5，几乎是 10 倍Transformer-big 模型的在线推理加速，但它也很容易适应其他语言。我们的代码可在 https://github.com/AutoTemp/Shallow-Aggressive-Decoding 获得。但它也很容易适应其他语言。我们的代码可在 https://github.com/AutoTemp/Shallow-Aggressive-Decoding 获得。但它也很容易适应其他语言。我们的代码可在 https://github.com/AutoTemp/Shallow-Aggressive-Decoding 获得。