//====================================================================
// Generate Word according the segmentation route
//====================================================================
private static WordResult[] GenerateWord(int[] uniPath, WordLinkedArray linkedArray, RowFirstDynamicArray <ChainContent> m_graphOptimum)
{
if (linkedArray.Count == 0)
{
return(null);
}
//--------------------------------------------------------------------
//Merge all seperate continue num into one number
MergeContinueNumIntoOne(ref linkedArray);
//--------------------------------------------------------------------
//The delimiter "－－"
ChangeDelimiterPOS(ref linkedArray);
//--------------------------------------------------------------------
//如果前一个词是数字，当前词以“－”或“-”开始，并且不止这一个字符，
//那么将此“－”符号从当前词中分离出来。
//例如 “3 / -4 / 月”需要拆分成“3 / - / 4 / 月”
SplitMiddleSlashFromDigitalWords(ref linkedArray);
//--------------------------------------------------------------------
//1、如果当前词是数字，下一个词是“月、日、时、分、秒、月份”中的一个，则合并,且当前词词性是时间
//2、如果当前词是可以作为年份的数字，下一个词是“年”，则合并，词性为时间，否则为数字。
//3、如果最后一个汉字是"点" ，则认为当前数字是时间
//4、如果当前串最后一个汉字不是"∶·．／"和半角的'.''/'，那么是数
//5、当前串最后一个汉字是"∶·．／"和半角的'.''/'，且长度大于1，那么去掉最后一个字符。例如"1."
CheckDateElements(ref linkedArray);
//--------------------------------------------------------------------
//输出结果
WordResult[] result = new WordResult[linkedArray.Count];
WordNode pCur = linkedArray.first;
int i = 0;
while (pCur != null)
{
WordResult item = new WordResult();
item.sWord = pCur.theWord.sWord;
item.nPOS = pCur.theWord.nPOS;
item.dValue = pCur.theWord.dValue;
result[i] = item;
m_graphOptimum.SetElement(pCur.row, pCur.col, new ChainContent(item.dValue, item.nPOS, pCur.sWordInSegGraph));
pCur = pCur.next;
i++;
}
return(result);
}
//Unknown word recognition
//pWordSegResult:word Segmentation result;
//graphOptimum: The optimized segmentation graph
//graphSeg: The original segmentation graph
public bool Recognition(WordResult[] pWordSegResult, RowFirstDynamicArray <ChainContent> graphOptimum,
List <AtomNode> atomSegment, WordDictionary dictCore)
{
ChainItem <ChainContent> item;
int nStartPos = 0, j = 0, nAtomStart, nAtomEnd, nPOSOriginal;
double dValue;
m_roleTag.POSTagging(pWordSegResult, dictCore, m_dict);
//Tag the segmentation with unknown recognition roles according the core dictionary and unknown recognition dictionary
for (int i = 0; i < m_roleTag.m_nUnknownWordsCount; i++)
{
while (j < atomSegment.Count && nStartPos < m_roleTag.m_nUnknownWords[i, 0])
{
nStartPos += atomSegment[j++].sWord.Length;
}
nAtomStart = j;
while (j < atomSegment.Count && nStartPos < m_roleTag.m_nUnknownWords[i, 1])
{
nStartPos += atomSegment[j++].sWord.Length;
}
nAtomEnd = j;
if (nAtomStart < nAtomEnd)
{
item = graphOptimum.GetElement(nAtomStart, nAtomEnd);
if (item != null)
{
dValue = item.Content.eWeight;
nPOSOriginal = item.Content.nPOS;
}
else
{
dValue = Predefine.INFINITE_VALUE;
}
if (dValue > m_roleTag.m_dWordsPossibility[i])
{
//Set the element with less frequency
graphOptimum.SetElement(nAtomStart, nAtomEnd, new ChainContent(m_roleTag.m_dWordsPossibility[i], m_nPOS, m_sUnknownFlags));
}
}
}
return(true);
}
//====================================================================
// Func Name : GenerateWordNet
// Description: Generate the segmentation word net according
// the original sentence
// Parameters : sSentence: the sentence
// dictCore : core dictionary
// bOriginalFreq=false: output original frequency
// Returns : bool
//====================================================================
public static RowFirstDynamicArray <ChainContent> GenerateWordNet(List <AtomNode> atomSegment, WordDictionary coreDict)
{
string sWord = "", sMaxMatchWord;
int nPOSRet, nPOS, nTotalFreq;
double dValue = 0;
RowFirstDynamicArray <ChainContent> m_segGraph = new RowFirstDynamicArray <ChainContent>();
m_segGraph.SetEmpty();
// 将原子部分存入m_segGraph
for (int i = 0; i < atomSegment.Count; i++)//Init the cost array
{
if (atomSegment[i].nPOS == Predefine.CT_CHINESE)
{
m_segGraph.SetElement(i, i + 1, new ChainContent(0, 0, atomSegment[i].sWord));
}
else
{
sWord = atomSegment[i].sWord;//init the word
dValue = Predefine.MAX_FREQUENCE;
switch (atomSegment[i].nPOS)
{
case Predefine.CT_INDEX:
case Predefine.CT_NUM:
nPOS = -27904;//'m'*256
sWord = "未##数";
dValue = 0;
break;
case Predefine.CT_DELIMITER:
nPOS = 30464;//'w'*256;
break;
case Predefine.CT_LETTER:
nPOS = -28280; // -'n' * 256 - 'x';
dValue = 0;
sWord = "未##串";
break;
case Predefine.CT_SINGLE://12021-2129-3121
if (Regex.IsMatch(atomSegment[i].sWord, @"^(-?\d+)(\.\d+)?$"))
{
//匹配浮点数
{
nPOS = -27904; //'m'*256
sWord = "未##数";
}
}
else
{
nPOS = -28280; // -'n' * 256 - 'x'
sWord = "未##串";
}
dValue = 0;
break;
default:
nPOS = atomSegment[i].nPOS;//'?'*256;
break;
}
m_segGraph.SetElement(i, i + 1, new ChainContent(dValue, nPOS, sWord));//init the link with minimum
}
}
// 将所有可能的组词存入m_segGraph
for (int i = 0; i < atomSegment.Count; i++) //All the word
{
sWord = atomSegment[i].sWord; //Get the current atom
int j = i + 1;
while (j < atomSegment.Count && coreDict.GetMaxMatch(sWord, out sMaxMatchWord, out nPOSRet))
{
if (sMaxMatchWord == sWord) // 就是我们要找的词
{
WordInfo info = coreDict.GetWordInfo(sWord); // 该词可能就有多种词性
// 计算该词的所有词频之和
nTotalFreq = 0;
for (int k = 0; k < info.Count; k++)
{
nTotalFreq += info.Frequencies[k];
}
// 限制出现某些特殊词
if (sWord.Length == 2 && (sWord.StartsWith("年") || sWord.StartsWith("月")) && i >= 1 &&
(Utility.IsAllNum(atomSegment[i - 1].sWord) ||
Utility.IsAllChineseNum(atomSegment[i - 1].sWord)))
{
//1年内、1999年末
if ("末内中底前间初".IndexOf(sWord.Substring(1)) >= 0)
{
break;
}
}
// 如果该词只有一个词性，则存储，否则词性记录为 0
if (info.Count == 1)
{
m_segGraph.SetElement(i, j, new ChainContent(nTotalFreq, info.POSs[0], sWord));
}
else
{
m_segGraph.SetElement(i, j, new ChainContent(nTotalFreq, 0, sWord));
}
}
sWord += atomSegment[j++].sWord;
}
}
return(m_segGraph);
}