论文分享 -- > NLP -- > Neural machine Translation of Rare Words with Subword Units
本次总结的是一篇16年的关于NLP中分词操做的论文，论文连接Subword，参考的实现代码subword-nmt，许多论文方法（例如BERT等）都将该方法应用到分词处理上，相对于word-level和character-level，该方法取得了不错的效果。git 动机和创新点 机器翻译中，一般使用固定大小的词表，而在实际翻译场景中，应当是open-vocabulary。这就使得翻译数据集中的稀有词
相关文章
- 1. Information from parts of words: Subword Models
- 2. 【CS224n】Neural Machine Translation with Seq2Seq
- 3. 论文分享 -- > NLP -- > Language Models are Unsupervised Multitask Learners
- 4. 【CS224n】Lecture 12: Information from parts of words: Subword Models
- 5. [论文阅读笔记] Massive Exploration of Neural Machine Translation Architectures
- 6. 论文解读：Multimodal Machine Translation with Embedding Prediction
- 7. Neural machine translation by jointly learning to align and translate论文阅读笔记
- 8. 论文分享-->Attention-over-Attention Neural Networks for Reading Comprehension
- 9. 论文阅读——Unsupervised Neural Machine Translation with Indirect Supervision
- 10. 【cs224n-10】Information from parts of words (Subword Models)
- 更多相关文章...
- • Docker Machine - Docker教程
- • CAP理论是什么？ - NoSQL教程
- • Git五分钟教程
- • 算法总结-二分查找法
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。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Information from parts of words: Subword Models
- 2. 【CS224n】Neural Machine Translation with Seq2Seq
- 3. 论文分享 -- > NLP -- > Language Models are Unsupervised Multitask Learners
- 4. 【CS224n】Lecture 12: Information from parts of words: Subword Models
- 5. [论文阅读笔记] Massive Exploration of Neural Machine Translation Architectures
- 6. 论文解读：Multimodal Machine Translation with Embedding Prediction
- 7. Neural machine translation by jointly learning to align and translate论文阅读笔记
- 8. 论文分享-->Attention-over-Attention Neural Networks for Reading Comprehension
- 9. 论文阅读——Unsupervised Neural Machine Translation with Indirect Supervision
- 10. 【cs224n-10】Information from parts of words (Subword Models)