[NLG]A Working Memory Model for Task-oriented Dialog Response Generation
總述： memNN常用於在對話中引入KB的知識，然而之前的工作大多數把dialogue history和KB的memory混在一起，作者借鑑了心理學的研究。有個work memory（類似於電腦內存的感覺）可以和兩個記憶做交互，一個知識記憶（semantic memory），一個歷史記憶（episodic memory）.然後作者就設計了一個模型，將對話歷史作爲歷史記憶，將KB結構化知識作爲知識記
相關文章
- 1. Tips for Generation in Encoder-Decoder model
- 2. Guiding the Long-Short Term Memory Model for Image Caption Generation
- 3. 知識驅動對話-Learning to Select Knowledge for Response Generation in Dialog Systems-閱讀筆記
- 4. [Coling2018]SGM：Sequence Generation Model for Multi-Label Classification
- 5. Task-Oriented Conversation Generation Using Heterogeneous Memory Networks
- 6. linux 3個內存模型(flat memory model、discontiguous memory model、sparse memory model)
- 7. 帶你走進 JVM Memory Model
- 8. 論文筆記：基於外部知識的會話模型Learning to Select Knowledge for Response Generation in Dialog Systems
- 9. CUDA ---- Memory Model
- 10. Neural Response Generation via GAN with an Approximate Embedding Layer
- 更多相關文章...
- • ASP Response 對象 - ASP 教程
- • Swift for 循環 - Swift 教程
- • Flink 數據傳輸及反壓詳解
- • Docker容器實戰(六) - 容器的隔離與限制
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。
最新文章
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Tips for Generation in Encoder-Decoder model
- 2. Guiding the Long-Short Term Memory Model for Image Caption Generation
- 3. 知識驅動對話-Learning to Select Knowledge for Response Generation in Dialog Systems-閱讀筆記
- 4. [Coling2018]SGM：Sequence Generation Model for Multi-Label Classification
- 5. Task-Oriented Conversation Generation Using Heterogeneous Memory Networks
- 6. linux 3個內存模型(flat memory model、discontiguous memory model、sparse memory model)
- 7. 帶你走進 JVM Memory Model
- 8. 論文筆記：基於外部知識的會話模型Learning to Select Knowledge for Response Generation in Dialog Systems
- 9. CUDA ---- Memory Model
- 10. Neural Response Generation via GAN with an Approximate Embedding Layer