MITIE ner model
设置事情：
对于初学者来说，你可以下载哪些 包含注释文本的语料库从一个巨大的转储文件中English Language Model称为 total_word_feature_extractor.dat。
之后，从他们的 官方Git下载/克隆MITIE-Master Project。
如果您正在运行Windows O.S然后下载CMake。
如果您正在运行基于x64的Windows O.S，然后安装适用于C++编译器的Visual Studio 2015社区版。
下载后，将上述内容全部提取到文件夹中。
为VS，从2015年开始>应用程序> Visual Studio的开发者打开命令提示符，然后导航到Tools文件夹，你会看到5里面的子文件夹。
下一步是建立ner_conll，ner_stream，train_freebase_relation_detector和wordrep包，使用下面的CMake在Visual Studio开发人员命令提示符命令。
像这样：
对于ner_conll：
cd "C:\Users\xyz\Documents\MITIE-master\tools\ner_conll"
ⅰ）mkdir build ⅱ）cd build ⅲ）cmake -G "Visual Studio 14 2015 Win64" .. ⅳ）cmake --build . --config Release --target install
对于ner_stream：
cd "C:\Users\xyz\Documents\MITIE-master\tools\ner_stream"
ⅰ）mkdir build ⅱ）cd build ⅲ）cmake -G "Visual Studio 14 2015 Win64" .. ⅳ）cmake --build . --config Release --target install
对于train_freebase_relation_detector：
cd "C:\Users\xyz\Documents\MITIE-master\tools\train_freebase_relation_detector"
ⅰ）mkdir build ⅱ）cd build ⅲ）cmake -G "Visual Studio 14 2015 Win64" .. IV）cmake --build . --config Release --target install
对于wordrep：
cd "C:\Users\xyz\Documents\MITIE-master\tools\wordrep"
我）mkdir build II）cd build III）cmake -G "Visual Studio 14 2015 Win64" .. IV）cmake --build . --config Release --target install
后您建立他们，你会得到一些警告150-160，别担心。
现在，导航到"C:\Users\xyz\Documents\MITIE-master\examples\cpp\train_ner"
做一个JSON文件“data.json”使用Visual Studio代码手动注释文本，这样的事情：
{
"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和注释他们，训练数据越多，预测精度就越好。
这个带注释的JSON也可以通过jQuery或Angular等前端工具创建。但为了简洁起见，我手工创建了它们。
现在，解析我们带注释的JSON文件并将其传递给ner_training_instance的add_entity方法。
但是C++不支持反射来反序列化JSON，这就是为什么你可以使用这个库Rapid JSON Parser。从他们的Git页面下载软件包并将其放在"C:\Users\xyz\Documents\MITIE-master\mitielib\include\mitie"下。
现在我们必须自定义train_ner_example.cpp文件，以解析我们注释的自定义实体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();
}
}
的add_entity接受3个参数，所述标记化的字符串可以是矢量，自定义实体类型名称，一个字的在句子的起始索引和字的范围内。
现在我们必须通过在Developer Command Prompt Visual Studio中使用以下命令来构建ner_train_example.cpp。
1）cd "C:\Users\xyz\Documents\MITIE-master\examples\cpp\train_ner" 2）mkdir build 3）cd build 4）cmake -G "Visual Studio 14 2015 Win64" .. 5）cmake --build . --config Release --target install 6）cd Release
7）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"
在成功地执行上述我们将得到一个new_ner_model.dat文件，这是我们的话语的序列化和训练版本。
现在，该.dat文件可以传递给RASA或独立使用。
对于它传递给RASA：
充分利用config.json文件，如下所示：
{
"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
}