Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/valkmjolnir/word-embedding-skip-gram
skip-gram word embedding model by C++
https://github.com/valkmjolnir/word-embedding-skip-gram
machine-learning nlp skip-gram word-embedding
Last synced: 1 day ago
JSON representation
skip-gram word embedding model by C++
- Host: GitHub
- URL: https://github.com/valkmjolnir/word-embedding-skip-gram
- Owner: ValKmjolnir
- Created: 2019-12-11T05:51:59.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2024-10-31T17:04:10.000Z (14 days ago)
- Last Synced: 2024-10-31T18:18:04.557Z (14 days ago)
- Topics: machine-learning, nlp, skip-gram, word-embedding
- Language: C++
- Size: 97.7 KB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# word-embedding-skip-gram
skip-gram word embedding model by C++in header __nlp.h__
```C++
#include "word_lib.h"
#include "bp_network.h"
```in header __word_lib.h__
```C++
class wordlib
{
private:
std::list dictionary;
public:
wordlib();
~wordlib();
int get_place(std::string);
int lib_size();
bool search(std::string);
void add_word(std::string);
void add_word_from_file(std::string);
void print_lib();
void print_word(int);
std::string get_word(int);
};
```
this class is used to record all words that exist in training set.in header __bp_network.h__
```C++
struct neuron;
double tanh(double x);
double difftanh(double x);
double sigmoid(double x);
double diffsigmoid(double x);
class word2vec;
```
word2vec will help you __calculate each word's embedding vector__ and __output information on the screen and into the file__ .default input file's name is __"trainingset.txt"__ ,you can change it if you like in __word_embedding.cpp__ .
# the most important thing
If you want to change the length of vectors,please go to __bp_network.h__ and find this function: __void word2vec::initializing()__then change the __HNUM__ at the beginning, this parameter decides the length of vectors.