斷詞系統長詞優先法分為: 正向及反向，會產生岐異與未知詞上的問題，若是詞庫夠大就能解決了。
已解決了正反向優先詞重覆字問題 2018/4/09 15:00
已添加詞位標籤 2018/4/09 15:00
已修正正反向長詞優先順序錯誤 2018/10/15 11:45
優化程式碼撰寫 2019/01/01 16:45
已添加決策 2019/02/12 21:50
---顯示介面 (c#)---
已解決了正反向優先詞重覆字問題 2018/4/09 15:00
已添加詞位標籤 2018/4/09 15:00
已修正正反向長詞優先順序錯誤 2018/10/15 11:45
優化程式碼撰寫 2019/01/01 16:45
已添加決策 2019/02/12 21:50
---顯示介面 (c#)---
using System.Collections;
using System.Collections.Generic;
using UnityEngine;
using UnityEngine.UI;
public class Layout : LongWordsFirst2 {
public Text systemMessage, inputMessage, result, runStatus;
public InputField userField;
public Button buttonEnter;
public Button buttonRefill;
public Button exit;
public Image inputMessageBackground;
public Button Sort;
// 顯示文字結果
public Text resultText;
public Scrollbar scrollbarResult;
private int timeSort = 0;
///
/// 確定
///
void btnOnClick_Enter()
{
cuttingReady();
}
///
/// 重填
///
void btnOnClick_Refill()
{
/*inputFieldType(userField, 0.6f, 1, 1, 1).text = "";
messageType = "";*/
Application.LoadLevel("NLTK_NEW");
}
///
/// 顯示結果
///
void btnOnClick_Sort()
{
try
{
StartCoroutine(logWordResultSystematics());
resultTextType(resultText).text = resultMessageType; // display result Message
}
catch { }
}
///
/// 離開應用程式
///
void btnOnClick_Exit()
{
Application.Quit();
MySQL.MySQL.closeSqlConnection();
}
///
/// button Component
/// btn: button Obj
/// width / height: button Obj posistion
/// sizeX / sizeY: button Obj size
///
///
///
///
///
///
///
/// inputField Component
/// InputField: inputField Obj
/// message: sentence message
/// width / height: inputField Obj posistion
/// sizeX / sizeY: inputField size
///
///
///
///
///
///
///
///
/// scrollbarType
/// Scrollbar: scrollbar obj
/// width / height: scrollbar obj posistion
/// sizeX / sizeY: scrollbar obj size
///
///
///
///
///
///
///
/// ImageType
/// Image: image obj
/// width / height: image obj posistion
/// sizeX / sizeY: image obj size
///
///
///
///
///
///
///
/// resultTextType
///
///
///
---語料庫類別(c#)---
using System.Collections.Generic;
using System.Data;
using System;
using MySql.Data.MySqlClient;
using System.Text;
namespace MySQL
{
public class MySQL
{
public static MySqlConnection mySqlConnection;
// DataBase Ip;
private static string HOST = "***.***.***.***";
public static string HOST_TYPE
{
set { HOST = value; }
get { return HOST; }
}
// DataBase user Id
private static string ID = "********";
public static string ID_TYPE
{
set { ID = value; }
get { return ID; }
}
// DataBase password
private static string PASSWORD = "******";
public static string PASSWORD_TYPE
{
set { PASSWORD = value; }
get { return PASSWORD; }
}
// DataBase Name
private static string DATABASE = "*****";
public static string DATABASE_TYPE
{
set { DATABASE = value; }
get { return DATABASE; }
}
private static string PORT = "****";
public static string PORT_TYPE
{
set { PORT = value; }
get { return PORT; }
}
// 連線結果
public static string RESULT = "";
// Connect to SQL
public static void OpenSqlConnection(string connction)
{
try
{
mySqlConnection = new MySqlConnection(connction);
mySqlConnection.Open();
RESULT = mySqlConnection.ServerVersion;
}
catch
{
RESULT = "無法連接資料庫";
}
}
// Close Sql
public static void closeSqlConnection()
{
mySqlConnection.Close();
mySqlConnection.Dispose();
mySqlConnection = null;
}
// SQL Query
public static void DOQUERY(string sqlQuery)
{
IDbCommand dbcommand = mySqlConnection.CreateCommand();
dbcommand.CommandText = sqlQuery;
IDataReader reader = dbcommand.ExecuteReader();
reader.Close();
reader = null;
dbcommand.Dispose();
dbcommand = null;
}
// Get DataSet
public static DataSet GetDataSet(string sqlString)
{
DataSet ds = new DataSet();
try
{
MySqlDataAdapter da = new MySqlDataAdapter(sqlString, mySqlConnection);
}
catch (Exception e)
{
throw new Exception("SQL:" + sqlString + "\n");
}
return ds;
}
///
/// string to uft8
/// message: sentence
///
///
///
/// INQUIRE_DATABASE
/// * dataBaseTitle : DataBaseName
/// * dataBaseTitle : DataBaseName
/// * numberingType : 0(Message)、1(Words)、2(Mark)、3(Words2)、4(Mark2)、5(Lexical)
/// * message: message
///
///
///
///
///
/// 詞性標記顯示
/// words: dataBase table[1]
///
///
///
---斷詞工具 (c#)---
using System.Collections;
using System.Collections.Generic;
using System.Text.RegularExpressions;
namespace SegmentationSymbolTool
{
public class SegmentationSymbol2
{
// 斷詞標記括號
private string[] specialSymbol = new string[] { "(", ")" };
// 斷字狀態
private string statusBroken;
// 刪除特殊符號
public string delectSymbol(string userMessage)
{
string strs = userMessage;
for (int x = 0; x < specialSymbol.Length; x++)
strs = strs.Replace(specialSymbol[x], " ");
return strs;
}
///
/// 斷字字數
/// status: sentence Lenght
///
///
private void status_conter(int status)
{
statusBroken = "";
for (int x = 0; x <= status; x++)
statusBroken += @"\S";
}
///
/// 刪除訊息
/// message: sentence
/// status: Hyphenation state
///
///
///
///
/// 斷字狀態
/// message: sentence
/// status: Hyphenation state
///
///
///
/// brokenSatus(string message, int status)
{
status_conter(status);
List match = new List();
MatchCollection splitResult = Regex.Matches(message, statusBroken, RegexOptions.IgnoreCase);
foreach (Match test in splitResult)
match.Add(test);
return match;
}
///
/// 組合處理
/// message: sentence
/// int: Hyphenation state
///
///
///
/// delect_Word_Combination(string message, int status)
{
status_conter(status);
string str = message;
List match = new List();
List stringList = new List();
MatchCollection splitResult = Regex.Matches(str, statusBroken, RegexOptions.IgnoreCase);
foreach (Match test in splitResult)
match.Add(test.ToString());
foreach (string strs in match)
{
stringList.Add(str.Replace(strs, ""));
return stringList;
}
return stringList;
}
///
/// 斷字處理
/// message: sentence
/// status: Hyphenation state
///
///
///
/// delect_oneWord(string message, int status)
{
status_conter(status);
string str = message;
List match = new List();
List stringList = new List();
MatchCollection splitResult = Regex.Matches(str, statusBroken, RegexOptions.IgnoreCase);
foreach (Match test in splitResult)
match.Add(test.ToString());
foreach (string strs in match)
stringList.Add(str.Replace(strs, ""));
return stringList;
}
///
/// grammarCombinationModule
/// speech1: mark
/// speech2: mark
///
///
///
///
---斷詞與其他功能類別 (c#)---
using System.Collections;
using System.Collections.Generic;
using UnityEngine;
using System.Text.RegularExpressions;
using System;
public class LongWordsFirst2 : MonoBehaviour
{
// 斷詞工具
private SegmentationSymbolTool.SegmentationSymbol2 segmentationSybolTool = new SegmentationSymbolTool.SegmentationSymbol2();
// 斷字系統資料表
private static string dataBasetitle = "glossary";
// 顯示結果
private string resultMessage;
public string resultMessageType
{
get { return resultMessage; }
}
// 使用者輸入句子
private string message = "";
public string messageType
{
set { message = value; }
get { return message; }
}
// 正向長詞優先
public string logeWordForward;
// 反向長詞優先
public string logeWordReverse;
public string logeWordReverseType
{
get { return logeWordReverse; }
}
// 正向長詞優先長度, 反向長詞優先長度, 組合長度
private int logeWordForwadLenght, logeWordReverseLenght;
// 正向長詞優先結果
private List logeWordForwardFunctionList = new List();
public List logeWordForwardFunctionListType
{
get { return logeWordForwardFunctionList; }
}
// 反向長詞優先結果
private List logeWordReverseFunctuinList = new List();
// 正向長詞優先標記結果
private List logeWordForwardLexicalFunctionList = new List();
public List logeWordForwardLexicalFunctionListType
{
get { return logeWordForwardLexicalFunctionList; }
}
// 反向長詞優先結果
public List logeWordReverseLexicalFunctionList = new List();
public List logeWordReverseLexicalFunctionListType
{
get { return logeWordReverseLexicalFunctionList; }
}
// 反向長詞方向校正結果
public List logeWordReverseCorrectionList = new List();
public List logeWordReverseCorrectionListType
{
get { return logeWordReverseCorrectionList; }
}
// 正向長詞優先詞性變化
private List logeWordForwardMark1List = new List();
public List logeWordForwardMark1Type
{
get { return logeWordForwardMark1List; }
}
// 反向長詞優先詞性變化
private List logeWordReverseMark1List = new List();
public List logeWordReverseMark1Tpye
{
get { return logeWordReverseMark1List; }
}
// 決策結果
public List decision_Realut = new List();
public List decision_RealutType
{
get{return decision_Realut;}
}
// 正向長詞變化組合合法
private List legitimateLogeWord= new List();
// 反向長詞變化組合合法
private List legitimateLogeReverse = new List();
// 詞性組合合法 List
private List mark_Legitimate1= new List();
private List mark_Legitimate2 = new List();
public bool decisionSw1 = true, decisionSw2 = true, decisionSw1_1 = true; // 變化1決策
public bool decisionSw3 = true, decisionSw4 = true, decisionSw3_3 = true; // 變化2決策
// 打開資料庫
public void OpenDataBase()
{
string connectionString = string.Format("Server = {0}; Database = {1}; UserID = {2}; Password = {3}; Port = {4};", MySQL.MySQL.HOST_TYPE, MySQL.MySQL.DATABASE_TYPE, MySQL.MySQL.ID_TYPE, MySQL.MySQL.PASSWORD_TYPE, MySQL.MySQL.PORT_TYPE);
MySQL.MySQL.OpenSqlConnection(connectionString);
}
///
/// 關閉資料庫
///
public void closeDataBase()
{
MySQL.MySQL.closeSqlConnection();
}
///
/// 切字準備
/// 優先執行
///
public void cuttingReady()
{
logeWordForward = message;
logeWordReverse = message;
logeWordForwadLenght = logeWordForward.Length;
logeWordReverseLenght = logeWordReverse.Length;
// 清除List
logeWordForwardFunctionList.Clear();
logeWordReverseFunctuinList.Clear();
logeWordForwardLexicalFunctionList.Clear();
logeWordReverseLexicalFunctionList.Clear();
logeWordReverseCorrectionList.Clear();
logeWordForwardMark1List.Clear();
logeWordReverseMark1List.Clear();
mark_Legitimate1.Clear();
legitimateLogeWord.Clear();
legitimateLogeReverse.Clear();
mark_Legitimate2.Clear();
decision_Realut.Clear();
// 執行正向長詞優先
StartCoroutine(loneWordForwardFunction());
// 執行反向長詞優先
StartCoroutine(longWordReverseFunction(0));
// 正向長詞優先詞位標記
StartCoroutine(logeWordForwardLexicalFunction(logeWordForwardFunctionList, logeWordForwardLexicalFunctionList));
// 反向長詞優先方校校正
StartCoroutine(logeWordReverseCorrectionFunction());
// 反向長詞優先詞位標記
StartCoroutine(logeWordForwardLexicalFunction(logeWordReverseCorrectionList, logeWordReverseLexicalFunctionList));
// 正向長詞優先詞性變化1
StartCoroutine(logeMakesFunction());
// 詞性組合決策
StartCoroutine(grmmarDecisionMaking());
// 句子組合
StartCoroutine(sentenceCombination());
}
///
/// 檢查沒有數據
/// Message: contence
/// Database No Data
///
///
///
/// list)
{
string str = message;
foreach (string str1 in list)
{
str = str.Replace(str1, "");
}
return str;
}
///
/// 反向長詞優先校正
///
IEnumerator logeWordReverseCorrectionFunction()
{
string str = "";
while (true)
{
if (logeWordReverse.Equals(""))
{
for (int x = logeWordReverseFunctuinList.Count-1; x >= 0; x--)
logeWordReverseCorrectionList.Add(logeWordReverseFunctuinList[x]);
break;
}
yield return new WaitForSeconds(0.5f);
}
}
///
/// 詞位標籤
/// longWord: positive longWord / reverse longWord
/// LexicalResult: positive longWord Result / reverse longWord Result
///
///
///
/// longWord, List LexicalResult)
{
int number = 0;
while (true)
{
if (logeWordForward.Equals(""))
{
foreach (string str in longWord)
{
LexicalResult.Add(MySQL.MySQL.INQUIRE_DATABASE(dataBasetitle, 5, str));
number += 1;
}
// 限制迴圈執行
if (number <= longWord.Count)
break;
}
yield return new WaitForSeconds(0.5f);
}
}
///
/// 正向長詞優先
/// IEnumerator: unity執行序
///
///
/// 後向長詞優先
/// lenght: sentence lenght
/// IEnumerator: unity 執行序
///
///
///
/// logeMakesFunction
/// Variety1 and Variety2
///
///
/// grmmarDecisionMaking
///
/// mark_Legitimate2.Count)
decision_Realut = logeWordForwardFunctionList;
}else if(decisionSw3 && decisionSw3_3 && decisionSw4){
if(mark_Legitimate1.Count < mark_Legitimate2.Count)
decision_Realut = logeWordReverseCorrectionList;
}else if(decisionSw1 && decisionSw1_1 && decisionSw2
&& decisionSw3 && decisionSw3_3 && decisionSw4)
decision_Realut.Add("兩個句子都可以");
}
}
///
/// sentenceCombination
///
/// Mark_LegitimateFunction2(List MarList){
string str = "";
if(MarList.Count != null){
for(int x=0; x Mark_LegitimateFunction1(List MarList){
string str = "";
if(MarList.Count != null){
for(int x=0; x
/// result Systematics
///
///
沒有留言:
張貼留言