Txt2Vec is a toolkit to represent text by vector. It's based on Google's word2vec project, but with some new features, such incremental training, model vector and so on.
I only want to know if is there any way in Txt2Vec for loading a plain text matrix to make a bin model for using in Txt2Vec. In other words. Having a well formed plain text matrix (according to Dump) been able to load in Txt2Vec .
lock (syn1Locker[target]) { for (int c = 0; c < layer1_size; c++) f += neu1[c] * syn1[c + l2];
After this a variable g (float) is generated, (it seems strange) BUT MANY times this variable 'g' gets its value of 0.0 , then it's nonsense to update all the vectors, simply add if (g == 0) continue;
that's it!
I've traced it many times, and it really get zero value too many times
and it's silly to update a vector with nothing!!
may you tell me how to start training word. When i am opening the visual studios project i can debug it or use the .exe, but how i gonna go to use it? I want to get vectors of some words. Unfortunately i do not know how to build a corpus or doing a training after that.