设置:
对于初学者,您可以下载
English Language Model
哪一个
包含一个名为
total\u word\u feature\u提取器。dat公司
.
之后,下载/克隆
MITIE-Master Project
从他们的
官方Git。
如果您正在运行Windows O.S,请下载
CMake
.
如果您运行的是基于x64的Windows操作系统,请安装Visual Studio
C++编译器的2015社区版。
下载上述内容后,将其全部解压缩到一个文件夹中。
从开始为VS 2015打开开发者命令提示符>所有应用程序>然后导航到tools文件夹,您将在其中看到5个子文件夹。
下一步是通过在Visual Studio Developer命令提示符中使用以下Cmake命令来构建ner\u conll、ner\u stream、train\u freebase\u relation\u detector和wordrep包。
类似这样:
对于ner_conll:
cd "C:\Users\xyz\Documents\MITIE-master\tools\ner_conll"
一)
mkdir build
ii)
cd build
iii)
cmake -G "Visual Studio 14 2015 Win64" ..
四)
cmake --build . --config Release --target install
对于ner_流:
cd "C:\Users\xyz\Documents\MITIE-master\tools\ner_stream"
一)
mkdir生成
ii)
cd构建
cmake—构建--配置发布--目标安装
cd "C:\Users\xyz\Documents\MITIE-master\tools\train_freebase_relation_detector"
一)
mkdir生成
ii)
cmake-G“Visual Studio 14 2015 Win64”。。
cmake—构建--配置发布--目标安装
对于wordrep:
cd "C:\Users\xyz\Documents\MITIE-master\tools\wordrep"
一)
mkdir生成
cd构建
iii)
cmake-G“Visual Studio 14 2015 Win64”。。
四)
cmake—构建--配置发布--目标安装
在您构建它们之后,您将收到大约150-160个警告,不要担心。
现在,导航到
"C:\Users\xyz\Documents\MITIE-master\examples\cpp\train_ner"
使用Visual Studio代码制作JSON文件“data.JSON”以手动注释文本,如下所示:
{
"AnnotatedTextList": [
{
"text": "I want to travel from New Delhi to Bangalore tomorrow.",
"entities": [
{
"type": "FromCity",
"startPos": 5,
"length": 2
},
{
"type": "ToCity",
"startPos": 8,
"length": 1
},
{
"type": "TimeOfTravel",
"startPos": 9,
"length": 1
}
]
}
]
}
您可以添加更多的话语并对其进行注释,训练数据越多,预测精度越好。
这种带注释的JSON也可以通过jQuery或Angular等前端工具创建。但为了简单起见,我手工制作了它们。
现在,解析带注释的JSON文件并将其传递给ner\u training\u实例的add\u entity方法。
但是C++不支持反射来反序列化JSON,这就是为什么您可以使用这个库
Rapid JSON Parser
. 从他们的Git页面下载包并将其放在
"C:\Users\xyz\Documents\MITIE-master\mitielib\include\mitie"
现在我们必须自定义train\u ner\u示例。cpp文件,以便解析带注释的自定义实体JSON,并将其传递给MITIE进行训练。
#include "mitie\rapidjson\document.h"
#include "mitie\ner_trainer.h"
#include <iostream>
#include <vector>
#include <list>
#include <tuple>
#include <string>
#include <map>
#include <sstream>
#include <fstream>
using namespace mitie;
using namespace dlib;
using namespace std;
using namespace rapidjson;
string ReadJSONFile(string FilePath)
{
ifstream file(FilePath);
string test;
cout << "path: " << FilePath;
try
{
std::stringstream buffer;
buffer << file.rdbuf();
test = buffer.str();
cout << test;
return test;
}
catch (exception &e)
{
throw std::exception(e.what());
}
}
//Helper function to tokenize a string based on multiple delimiters such as ,.;:- or whitspace
std::vector<string> SplitStringIntoMultipleParameters(string input, string delimiter)
{
std::stringstream stringStream(input);
std::string line;
std::vector<string> TokenizedStringVector;
while (std::getline(stringStream, line))
{
size_t prev = 0, pos;
while ((pos = line.find_first_of(delimiter, prev)) != string::npos)
{
if (pos > prev)
TokenizedStringVector.push_back(line.substr(prev, pos - prev));
prev = pos + 1;
}
if (prev < line.length())
TokenizedStringVector.push_back(line.substr(prev, string::npos));
}
return TokenizedStringVector;
}
//Parse the JSON and store into appropriate C++ containers to process it.
std::map<string, list<tuple<string, int, int>>> FindUtteranceTuple(string stringifiedJSONFromFile)
{
Document document;
cout << "stringifiedjson : " << stringifiedJSONFromFile;
document.Parse(stringifiedJSONFromFile.c_str());
const Value& a = document["AnnotatedTextList"];
assert(a.IsArray());
std::map<string, list<tuple<string, int, int>>> annotatedUtterancesMap;
for (int outerIndex = 0; outerIndex < a.Size(); outerIndex++)
{
assert(a[outerIndex].IsObject());
assert(a[outerIndex]["entities"].IsArray());
const Value &entitiesArray = a[outerIndex]["entities"];
list<tuple<string, int, int>> entitiesTuple;
for (int innerIndex = 0; innerIndex < entitiesArray.Size(); innerIndex++)
{
entitiesTuple.push_back(make_tuple(entitiesArray[innerIndex]["type"].GetString(), entitiesArray[innerIndex]["startPos"].GetInt(), entitiesArray[innerIndex]["length"].GetInt()));
}
annotatedUtterancesMap.insert(pair<string, list<tuple<string, int, int>>>(a[outerIndex]["text"].GetString(), entitiesTuple));
}
return annotatedUtterancesMap;
}
int main(int argc, char **argv)
{
try {
if (argc != 3)
{
cout << "You must give the path to the MITIE English total_word_feature_extractor.dat file." << endl;
cout << "So run this program with a command like: " << endl;
cout << "./train_ner_example ../../../MITIE-models/english/total_word_feature_extractor.dat" << endl;
return 1;
}
else
{
string filePath = argv[2];
string stringifiedJSONFromFile = ReadJSONFile(filePath);
map<string, list<tuple<string, int, int>>> annotatedUtterancesMap = FindUtteranceTuple(stringifiedJSONFromFile);
std::vector<string> tokenizedUtterances;
ner_trainer trainer(argv[1]);
for each (auto item in annotatedUtterancesMap)
{
tokenizedUtterances = SplitStringIntoMultipleParameters(item.first, " ");
mitie::ner_training_instance *currentInstance = new mitie::ner_training_instance(tokenizedUtterances);
for each (auto entity in item.second)
{
currentInstance -> add_entity(get<1>(entity), get<2>(entity), get<0>(entity).c_str());
}
// trainingInstancesList.push_back(currentInstance);
trainer.add(*currentInstance);
delete currentInstance;
}
trainer.set_num_threads(4);
named_entity_extractor ner = trainer.train();
serialize("new_ner_model.dat") << "mitie::named_entity_extractor" << ner;
const std::vector<std::string> tagstr = ner.get_tag_name_strings();
cout << "The tagger supports " << tagstr.size() << " tags:" << endl;
for (unsigned int i = 0; i < tagstr.size(); ++i)
cout << "\t" << tagstr[i] << endl;
return 0;
}
}
catch (exception &e)
{
cerr << "Failed because: " << e.what();
}
}
add_实体接受3个参数,标记化字符串可以是向量,自定义实体类型名称,句子中单词的开始索引和单词的范围。
现在我们必须构建ner\u train\u示例。通过在开发人员命令提示符Visual Studio中使用以下命令进行cpp。
1)
cd "C:\Users\xyz\Documents\MITIE-master\examples\cpp\train_ner"
2)
mkdir生成
3)
cd构建
4)
cmake-G“Visual Studio 14 2015 Win64”。。
5)
6)
cd Release
train_ner_example "C:\\Users\\xyz\\Documents\\MITIE-master\\MITIE-models\\english\\total_word_feature_extractor.dat" "C:\\Users\\xyz\\Documents\\MITIE-master\\examples\\cpp\\train_ner\\data.json"
成功执行上述操作后,我们将得到一个新的NU ner_模型。dat文件,是我们话语的序列化和训练版本。
既然dat文件可以传递给RASA或单独使用。
将其传递给RASA:
进行配置。json文件如下:
{
"project": "demo",
"path": "C:\\Users\\xyz\\Desktop\\RASA\\models",
"response_log": "C:\\Users\\xyz\\Desktop\\RASA\\logs",
"pipeline": ["nlp_mitie", "tokenizer_mitie", "ner_mitie", "ner_synonyms", "intent_entity_featurizer_regex", "intent_classifier_mitie"],
"data": "C:\\Users\\xyz\\Desktop\\RASA\\data\\examples\\rasa.json",
"mitie_file" : "C:\\Users\\xyz\\Documents\\MITIE-master\\examples\\cpp\\train_ner\\Release\\new_ner_model.dat",
"fixed_model_name": "demo",
"cors_origins": ["*"],
"aws_endpoint_url": null,
"token": null,
"num_threads": 2,
"port": 5000
}