-
大小: 3.85MB文件類型: .rar金幣: 2下載: 0 次發布日期: 2023-08-13
- 語言: C#
- 標簽: NLPIR??ICTCLS2013??分詞??C#??
資源簡介
NLPIR(ICTCLAS2013)是由張華平博士發布的中文分詞系統,可用多種語言進行二次開發,該資源是用C#語言在VS2010環境下在http://www.nlpir.org/提供的原示例基礎上進行改進后的示例程序。

代碼片段和文件信息
using?System;
using?System.IO;
using?System.Runtime.InteropServices;
using?System.Text;
namespace?Example
{
????///?
????///?標注集類型。
????///?
????public?enum?NLPIR_MAP
????{
????????///?
????????///?計算所一級標注集。
????????///?
????????ICT_POS_MAP_FIRST?=?1
????????///?
????????///?計算所二級標注集。
????????///?
????????ICT_POS_MAP_SECOND?=?0
????????///?
????????///?北大一級標注集。
????????///?
????????PKU_POS_MAP_FIRST?=?3
????????///?
????????///?北大二級標注集。
????????///?
????????PKU_POS_MAP_SECOND?=?2
????}
????///?
????///?編碼類型。
????///?
????public?enum?NLPIR_CODE
????{
????????///?
????????///?GBK編碼。
????????///?
????????GBK_CODE?=?0
????????///?
????????///?UTF8編碼。
????????///?
????????UTF8_CODE?=?1
????????///?
????????///?BIG5編碼。
????????///?
????????BIG5_CODE?=?2
????????///?
????????///?GBK編碼,里面包含繁體字。
????????///?
????????GBK_FANTI_CODE?=?3
????}
????///?
????///?分詞結果結構體。
????///?
????[StructLayout(LayoutKind.Sequential)]
????public?struct?result_t
????{
????????///?
????????///?詞語在輸入句子中的開始位置。
????????///?
????????public?int?start;
????????///?
????????///?詞語的長度。
????????///?
????????public?int?length;
????????///?
????????///?詞性ID值,可以快速的獲取詞性表。
????????///?
????????[MarshalAsAttribute(UnmanagedType.ByValTStr?SizeConst?=?40)]
????????public?string?sPos;
????????///?
????????///?詞性標注的編號。
????????///?
????????public?int?POS_id;
????????///?
????????///?該詞的內部ID號,如果是未登錄詞,設成0或者-1。
????????///?
????????public?int?word_ID;
????????///?
????????///?區分用戶詞典,1是用戶詞典中的詞,0非用戶詞典中的詞。
????????///?
????????public?int?word_type;
????????///?
????????///?權值。
????????///?
????????public?int?weight;
????}
????///?
????///?分詞類。
????///?
????public?class?NLPIR
????{
????????#region?對變量進行聲明
????????private?static?bool?_Init?=?false;
????????private?static?bool?_NWIStart?=?false;
????????private?static?bool?_NWIComplete?=?false;
????????private?const?string?rootDir?=?@“.\“;
????????#endregion
????????#region?對函數進行聲明和包裝
????????#region?預判斷
????????private?static?void?JudgeInit()
????????{
????????????if?(!_Init)?throw?new?Exception(“未進行初始化!“);
????????}
????????private?static?void?JudgeNWIStart()
????????{
????????????JudgeInit();
????????????if?(!_NWIStart)?throw?new?Exception(“未啟動新詞識別!“);
????????}
????????private?static?void?JudgeNWIComplete()
????????{
????????????JudgeInit();
????????????if?(!_NWIComplete)?throw?new?Exception(“未結束新詞識別!“);
????????}
????????#endregion
????????#region?初始化、退出
????????///?
????????///?初始化。
????????///?
????????///?
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件????????144??2013-12-02?16:21??NLPIR_C#\app.config
?????文件?????286196??2012-05-18?21:36??NLPIR_C#\bin\Data\BIG2GBK.map
?????文件?????468456??2012-05-18?21:33??NLPIR_C#\bin\Data\BIG5.pdat
?????文件?????158695??2012-05-18?21:33??NLPIR_C#\bin\Data\BIG5.wordlist
?????文件????3520144??2009-01-16?13:48??NLPIR_C#\bin\Data\BiWord.big
?????文件??????65540??2012-11-08?20:45??NLPIR_C#\bin\Data\charset.type
?????文件????????856??2013-12-03?21:57??NLPIR_C#\bin\Data\Configure.xm
?????文件????1696620??2009-01-16?13:48??NLPIR_C#\bin\Data\CoreDict.pdat
?????文件????1786424??2009-01-16?13:48??NLPIR_C#\bin\Data\CoreDict.pos
?????文件?????478168??2009-01-16?13:48??NLPIR_C#\bin\Data\CoreDict.unig
?????文件?????262236??2013-12-07?12:41??NLPIR_C#\bin\Data\FieldDict.pdat
?????文件?????????30??2013-12-07?12:41??NLPIR_C#\bin\Data\FieldDict.pos
?????文件?????549204??2012-05-18?21:34??NLPIR_C#\bin\Data\GBK.pdat
?????文件?????166985??2012-05-18?21:34??NLPIR_C#\bin\Data\GBK.wordlist
?????文件?????286196??2012-05-18?21:36??NLPIR_C#\bin\Data\GBK2BIG.map
?????文件?????286196??2012-05-18?21:37??NLPIR_C#\bin\Data\GBK2GBKC.map
?????文件?????286196??2012-05-18?21:37??NLPIR_C#\bin\Data\GBK2UTF.map
?????文件?????550848??2012-12-22?11:50??NLPIR_C#\bin\Data\GBKA.pdat
?????文件?????166985??2012-12-22?11:50??NLPIR_C#\bin\Data\GBKA.wordlist
?????文件?????286196??2012-12-22?11:50??NLPIR_C#\bin\Data\GBKA2UTF.map
?????文件?????550848??2012-05-18?21:34??NLPIR_C#\bin\Data\GBKC.pdat
?????文件?????166985??2012-05-18?21:34??NLPIR_C#\bin\Data\GBKC.wordlist
?????文件?????286196??2012-05-18?21:37??NLPIR_C#\bin\Data\GBKC2GBK.map
?????文件????1978128??2009-01-16?13:48??NLPIR_C#\bin\Data\GranDict.pdat
?????文件????1778776??2009-01-16?13:48??NLPIR_C#\bin\Data\GranDict.pos
?????文件????????406??2009-01-16?13:48??NLPIR_C#\bin\Data\ICTPOS.map
?????文件???????3229??2013-12-07?12:41??NLPIR_C#\bin\Data\NewWord.lst
?????文件??????37253??2009-01-16?13:48??NLPIR_C#\bin\Data\NLPIR.ctx
?????文件???????3356??2013-11-15?12:29??NLPIR_C#\bin\Data\NLPIR.user
?????文件????????288??2009-01-16?13:48??NLPIR_C#\bin\Data\NLPIR_First.map
............此處省略47個文件信息
評論
共有 條評論