论文阅读：Neural Machine Translation with Byte-Level Subwords
文章简介： 基于字符，子词，词的机器翻译几乎都是以词频top-k数量建立的词典；但是针对字符相对杂乱的日文和字符较丰富的中文，往往他们的罕见词难以表示； 本文提出采用字节级别的字词BBPE(byte-level BPE)，不会出现oov的词；比纯用字节表示更方便，比只用字符表示又效果更好；当BBPE和BPE性能接近时，词典size只是BPE的1/8； 主要方法： 整体思想是，把文本表示生字节级别的
相关文章
- 1. 论文阅读——Unsupervised Neural Machine Translation with Indirect Supervision
- 2. 论文阅读——Robust Unsupervised Neural Machine Translation with Adversarial Training
- 3. 论文阅读：Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
- 4. 论文阅读：ByteNet, Neural Machine Translation in Linear Time
- 5. Neural machine translation by jointly learning to align and translate论文阅读笔记
- 6. 【论文阅读】Neural Machine Translation By Jointly Learning To Align and Translate
- 7. [论文阅读笔记] Massive Exploration of Neural Machine Translation Architectures
- 8. 【论文阅读】Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
- 9. 论文解读：Multimodal Machine Translation with Embedding Prediction
- 10. 论文阅读——Toward Making the Most of Context in Neural Machine Translation
- 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——Unsupervised Neural Machine Translation with Indirect Supervision
- 2. 论文阅读——Robust Unsupervised Neural Machine Translation with Adversarial Training
- 3. 论文阅读：Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
- 4. 论文阅读：ByteNet, Neural Machine Translation in Linear Time
- 5. Neural machine translation by jointly learning to align and translate论文阅读笔记
- 6. 【论文阅读】Neural Machine Translation By Jointly Learning To Align and Translate
- 7. [论文阅读笔记] Massive Exploration of Neural Machine Translation Architectures
- 8. 【论文阅读】Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
- 9. 论文解读：Multimodal Machine Translation with Embedding Prediction
- 10. 论文阅读——Toward Making the Most of Context in Neural Machine Translation