katakombi / rnnlm Goto Github PK

I got the following error trying to compile in an Xcode project...
"/.../rnnlm-0.4b/fastexp.h:543:11: Constant expression evaluates to 9223372039002259456 which cannot be narrowed to type 'long long'"

Repeated 6 times for the three lines containing "v4sil (0x80000000)"
The macro (line 109) cast as "unsigned long long" but for some reason the compiler is seeing it as "long long" !

I also had issues with "exp10(...)" not recognized but I used "pow(10,...)" instead.

Hello, I am a chinese student . I have a question about testing,so i hope you help me solve this problem. I want to build a language model of chinese . I use sirlm to build a ngram language model of chinese and combine model of RNN,The result show that unexpected end of file . please tell me why?

Hi,

I downloaded the software from http://rnnlm.org/, so I am not sure if this is a good place to ask questions/report issues. I apologize if it is not.

I am trainig the sample model, and then I am trying to find the nbest using the following input:

$ cat best.txt

1 I AM
1 I AM
1 I AM
2 I AM
2 I AM
3 I AM
3 I AM
3 I AM
3 I AM

And I am getting the following output with the 0.4b version:

./rnnlm -rnnlm model -test best.txt -nbest

-3.888084
-3.529828
-3.529828
-3.558858
-3.558858
-3.561705
-3.561705
-3.561705
-3.561705

Whereas with the 0.2b version I get:

./rnnlm -rnnlm model -test best.txt -nbest

-3.912723
-3.912723
-3.912723
-3.158704
-3.158704
-3.160540
-3.160540
-3.160540
-3.160540

My questions are:

1- Shouldn't I get the same probabiliy for all the sentences, given that they are all equal?
2- Why is the 0.4b version returning a probability for the first sentence that is different than the probabilities of the other sentences that start with a "1"?

Thanks a lot!