[ACL2017]Neural Word Segmentation with Rich Pretraining
中文分詞的文章，非常有意思 之所以有意思是因爲這篇文章將transition-based的方法引入到了neural network, 而且用來分詞，當然transition-based用來做parsing的有很多文章，本文的關鍵問題是如何表示word, P, 和character. 並不是初始化而已，也是本文的創新點，就是pretraining word embedding, P embeddin
相關文章
- 1. Contextual Word Representations and Pretraining
- 2. Tokenisation &word segmentation & sentence segmentation
- 3. Review of Semantic Segmentation with Deep Learning
- 4. 00037-Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- 5. cs224n學習4： Contextual Word Representations and Pretraining
- 6. NLP基礎之——Contextual Word Representations and Pretraining
- 7. Rich feature hierarchies for accurate object detection and semantic segmentation
- 8. [NLG] Pretraining for Conditional Generation with Pseudo Self Attention
- 9. Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Le
- 10. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
- 更多相關文章...
- • XSLT
- • XSL-FO character 對象 - XSL-FO 教程
- • 算法總結-廣度優先算法
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Contextual Word Representations and Pretraining
- 2. Tokenisation &word segmentation & sentence segmentation
- 3. Review of Semantic Segmentation with Deep Learning
- 4. 00037-Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- 5. cs224n學習4： Contextual Word Representations and Pretraining
- 6. NLP基礎之——Contextual Word Representations and Pretraining
- 7. Rich feature hierarchies for accurate object detection and semantic segmentation
- 8. [NLG] Pretraining for Conditional Generation with Pseudo Self Attention
- 9. Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Le
- 10. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations