[NLG]Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
總述： 我覺得這篇論文的主要亮點就是不要標註數據。之前趙天成的zero-shot雖然很驚豔，但是迫於每一句話都需要標註dialogu action，所以應用性不強。這篇論文就是結合了趙天成之前的兩篇工作，第一個zero-shot，第二個laed（用於在大規模數據中學習找到對話潛在的latent action）。然後作者就認爲，在大規模無標籤對話中用laed學習可以學到隱式的dialog act
相關文章
- 1. Deep Reinforcement Learning for Dialogue Generation
- 2. Adversarial Learning for Neural Dialogue Generation 代碼分析
- 3. Deep Reinforcement Learning for Dialogue Generation閱讀筆記
- 4. Deep Reinforcement Learning for Dialogue Generation 論文閱讀 A Diversity-Promoting Objective Function fo
- 5. Geoffrey Hinton's Capsule Networks: A Novel Approach to Deep Learning
- 6. A Survey on Transfer Learning
- 7. transfer learning
- 8. A holistic approach to semi-supervised learning
- 9. An annotated path to start with Machine Learning
- 10. 論文筆記：Learning how to Active Learn: A Deep Reinforcement Learning Approach
- 更多相關文章...
- • ASP Transfer 方法 - ASP 教程
- • jQuery Mobile Data 屬性 - jQuery Mobile 教程
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
- • Java Agent入門實戰（一）-Instrumentation介紹與使用
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. Deep Reinforcement Learning for Dialogue Generation
- 2. Adversarial Learning for Neural Dialogue Generation 代碼分析
- 3. Deep Reinforcement Learning for Dialogue Generation閱讀筆記
- 4. Deep Reinforcement Learning for Dialogue Generation 論文閱讀 A Diversity-Promoting Objective Function fo
- 5. Geoffrey Hinton's Capsule Networks: A Novel Approach to Deep Learning
- 6. A Survey on Transfer Learning
- 7. transfer learning
- 8. A holistic approach to semi-supervised learning
- 9. An annotated path to start with Machine Learning
- 10. 論文筆記：Learning how to Active Learn: A Deep Reinforcement Learning Approach