Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如何预测 #21

Open
kscp123 opened this issue Apr 13, 2018 · 9 comments
Open

如何预测 #21

kscp123 opened this issue Apr 13, 2018 · 9 comments

Comments

@kscp123
Copy link

kscp123 commented Apr 13, 2018

这个实际使用怎么预测?如果候选集的答案很多计算会很慢吧

@white127
Copy link
Owner

可以增加一个前置的rank模块,用一个高性能、简单的算法进行答案初筛选

@kscp123
Copy link
Author

kscp123 commented Apr 25, 2018

多谢回复,那么大概训练多少轮可以收敛呢?我这跑了几千轮好像变化不大

@white127
Copy link
Owner

white127 commented Apr 26, 2018 via email

@kscp123
Copy link
Author

kscp123 commented Apr 26, 2018

这个确实是一般情况,但是在这个问题下好像不适用,因为这里跑的是你的代码,看到下面有人说10K+轮才开始有点效果,所以我就是想知道你跑了多少轮 @white127

@white127
Copy link
Owner

white127 commented Apr 26, 2018 via email

@kscp123
Copy link
Author

kscp123 commented Apr 27, 2018

还有个疑问就是这段代码万一pos和neg采到同一个,那岂不是会影响训练?虽然概率很小
pos = trainList[random.randint(0, len(trainList)-1)]
neg = trainList[random.randint(0, len(trainList)-1)]

@white127
Copy link
Owner

white127 commented Apr 27, 2018 via email

@zemu121
Copy link

zemu121 commented Oct 31, 2018

  1. 训练时并没有用到word2vec的向量结果,是随机赋初值的,对吗?
  2. 模型训练的结果是能将q和a准确的映射成向量吗,然后从候选答案中找出与q的向量距离最近的那个a作为正确答案?

@white127
Copy link
Owner

white127 commented Nov 7, 2018

  1. 训练时并没有用到word2vec的向量结果,是随机赋初值的,对吗?
  2. 模型训练的结果是能将q和a准确的映射成向量吗,然后从候选答案中找出与q的向量距离最近的那个a作为正确答案?

1.对
2.对

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants