Neural Response Generation via GAN with an Approximate Embedding Layer
1. Goal 用GAN来对dialogue system建模，从而减少safe response（e.g. “我不知道”, “我也是”）。 2. Contribution 提出了一个AEL (Approximate Embedding Layer )来解决seq2seq模型decode阶段由于sampling导致的不可微问题（non-differentiable problem）。 3. Mod
相关文章
- 1. 系列总结：Sequence Generation via GAN
- 2. Neural Headline Generation with Minimum Risk Training
- 3. Embedding Layer
- 4. Text Generation With LSTM Recurrent Neural Networks in Python with Keras
- 5. Fast Approximate Energy Minimization via Graph Cuts
- 6. (zhuan) Recurrent Neural Network
- 7. 论文阅读：Neural Image Caption Generation with Visual Attention
- 8. Deep Speaker: an End-to-End Neural Speaker Embedding System
- 9. 【读】seq2seq——（6）Neural Headline Generation with Minimum Risk Training
- 10. GAN(9)——sequence generation
- 更多相关文章...
- • ASP Response 对象 - ASP 教程
- • XSLT
- • Flink 数据传输及反压详解
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
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。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 系列总结：Sequence Generation via GAN
- 2. Neural Headline Generation with Minimum Risk Training
- 3. Embedding Layer
- 4. Text Generation With LSTM Recurrent Neural Networks in Python with Keras
- 5. Fast Approximate Energy Minimization via Graph Cuts
- 6. (zhuan) Recurrent Neural Network
- 7. 论文阅读：Neural Image Caption Generation with Visual Attention
- 8. Deep Speaker: an End-to-End Neural Speaker Embedding System
- 9. 【读】seq2seq——（6）Neural Headline Generation with Minimum Risk Training
- 10. GAN(9)——sequence generation