论文阅读——Aligned Cross Entropy for Non-Autoregressive Machine Translation
https://arxiv.org/pdf/2004.01655.pdf 对齐交叉熵的非自回归机器翻译（未开源） 非自回归机器翻译模型对整个目标序列进行并行预测，极大地提高了解码速度。然而由于模型中缺少自回归因子，难以对词序建模，且交叉熵损失会严重影响词序的微小变化，因此作者提出使用 aligned cross entropy 对齐交叉熵 AXE 作为非自回归模型的损失函数，AXE 使用一个可
相关文章
- 1. 论文阅读——Dual Learning for Machine Translation
- 2. 论文阅读：Dual Learning for Machine Translation
- 3. 论文阅读|Cross-Lingual Machine Reading Comprehension
- 4. Learning Cross-Aligned Latent Embeddings for Zero-Shot Cross-Modal Retrieval论文阅读笔记
- 5. 论文阅读——Modeling Future Cost for Neural Machine Translation
- 6. 论文 Non-Parametric Adaptation for Neural Machine Translation阅读笔记
- 7. 【论文阅读】Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
- 8. 论文阅读：Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
- 9. 《论文阅读》UCTGAN: Diverse Image Inpainting based on Unsupervised Cross-Space Translation
- 10. [论文解读] Cross-Entropy Based Testing
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • Docker Machine - Docker教程
- • JDK13 GA发布：5大特性解读
- • Scala 中文乱码解决
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文阅读——Dual Learning for Machine Translation
- 2. 论文阅读：Dual Learning for Machine Translation
- 3. 论文阅读|Cross-Lingual Machine Reading Comprehension
- 4. Learning Cross-Aligned Latent Embeddings for Zero-Shot Cross-Modal Retrieval论文阅读笔记
- 5. 论文阅读——Modeling Future Cost for Neural Machine Translation
- 6. 论文 Non-Parametric Adaptation for Neural Machine Translation阅读笔记
- 7. 【论文阅读】Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
- 8. 论文阅读：Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
- 9. 《论文阅读》UCTGAN: Diverse Image Inpainting based on Unsupervised Cross-Space Translation
- 10. [论文解读] Cross-Entropy Based Testing