search

zhanghainan / ReCoSa

ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
58 stars 9 forks source link

上下文输入 #6

Closed lost-person closed 5 years ago

lost-person commented 5 years ago

你好！十分感谢你的开源代码。只是在阅读时，有一处细节不太了解——在模型输入时，你将多轮的上下文拆解成多个样本。即，

The dialogue data：Hello How are you? Good, you? I'm fine, what's new? Souce looks like:

Hello How are you?

Hello How are you? Good, you?

Hello How are you? Good, you? I'm fine, what's new?

Target:

Good, you?

I'm fine, what's new?

Nothing much...

请问，这是多轮对话的通用处理方式吗？还是直接将多轮的上下文作为输入，也可以？

可能这个问题略显幼稚，但还是期待你的回复。

zhanghainan commented 4 years ago

为了扩大数据量，一般都是做拆分处理。因为设计多轮对话机器人，不可能只需要回答最后一句话，这显然是不合理的。为了让机器能够更多的学习，所以做了这种操作