lijiwei2-A Persona-Based Neural Conversation Model
使用person embedding embedding 的作用 蘊含背景和說話方式，解決了多輪對話中response不一致的問題。（換一種方式問問題，得到的答案不同）。 embedding的實現 具體的人物做背景標註昂貴，根據對話的回答聚類產生。 在target的E表示中加入speaker representation。每個source用戶綁定一個向量vi，在decode的時候和h_t,e_t（
相關文章
- 1. A Knowledge-Grounded Neural Conversation Model
- 2. A Persona-Based Neural Conversation Model論文
- 3. A Knowledge-Grounded Neural Conversation Model 翻譯
- 4. short text conversation: neural network
- 5. [dialog system]閱讀筆記 - 2016__A Persona-Based Neural Conversation Model
- 6. A Persona-Based Neural Conversation Model論文學習零散記錄
- 7. A Diversity-Promoting Objective Function for Neural Conversation
- 8. A Diversity-Promoting Objective Function for Neural Conversation Models
- 9. A Neural Conversational Model
- 10. neural topic model
- 更多相關文章...
- • Thymeleaf條件判斷 - Thymeleaf 教程
- • ionic 複選框 - ionic 教程
- • 常用的分佈式事務解決方案
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. A Knowledge-Grounded Neural Conversation Model
- 2. A Persona-Based Neural Conversation Model論文
- 3. A Knowledge-Grounded Neural Conversation Model 翻譯
- 4. short text conversation: neural network
- 5. [dialog system]閱讀筆記 - 2016__A Persona-Based Neural Conversation Model
- 6. A Persona-Based Neural Conversation Model論文學習零散記錄
- 7. A Diversity-Promoting Objective Function for Neural Conversation
- 8. A Diversity-Promoting Objective Function for Neural Conversation Models
- 9. A Neural Conversational Model
- 10. neural topic model