//====================================================================
// 准备PositionMap，用于记录词的位置
//====================================================================
private static int[] PreparePositionMap(RowFirstDynamicArray <ChainContent> aWord)
{
int[] m_npWordPosMapTable;
ChainItem <ChainContent> pTail, pCur;
int nWordIndex = 0, m_nWordCount;
//Get tail element and return the words count
m_nWordCount = aWord.GetTail(out pTail);
if (m_nWordCount > 0)
{
m_npWordPosMapTable = new int[m_nWordCount];
}
else
{
m_npWordPosMapTable = null;
}
//Record the position of possible words
pCur = aWord.GetHead();
while (pCur != null)
{
m_npWordPosMapTable[nWordIndex++] = pCur.row * Predefine.MAX_SENTENCE_LEN + pCur.col;
pCur = pCur.next;
}
return(m_npWordPosMapTable);
}
//====================================================================
// 生成两两词之间的二叉图表
//====================================================================
public static ColumnFirstDynamicArray <ChainContent> BiGraphGenerate(
RowFirstDynamicArray <ChainContent> aWord, double smoothPara, WordDictionary biDict, WordDictionary coreDict)
{
ColumnFirstDynamicArray <ChainContent> aBiWordNet = new ColumnFirstDynamicArray <ChainContent>();
ChainItem <ChainContent> pCur, pNextWords;
int nTwoWordsFreq = 0, nCurWordIndex, nNextWordIndex;
double dCurFreqency, dValue, dTemp;
string sTwoWords;
StringBuilder sb = new StringBuilder();
//Record the position map of possible words
int[] m_npWordPosMapTable = PreparePositionMap(aWord);
pCur = aWord.GetHead();
while (pCur != null)
{
if (pCur.Content.nPOS >= 0)
{
//It's not an unknown words
dCurFreqency = pCur.Content.eWeight;
}
else
{
//Unknown words
dCurFreqency = coreDict.GetFrequency(pCur.Content.sWord, 2);
}
//Get next words which begin with pCur.col（注：很特殊的对应关系）
pNextWords = aWord.GetFirstElementOfRow(pCur.col);
while (pNextWords != null && pNextWords.row == pCur.col)
{
sb.Remove(0, sb.Length);
sb.Append(pCur.Content.sWord);
sb.Append(Predefine.WORD_SEGMENTER);
sb.Append(pNextWords.Content.sWord);
sTwoWords = sb.ToString();
//Two linked Words frequency
nTwoWordsFreq = biDict.GetFrequency(sTwoWords, 3);
//Smoothing
dTemp = 1.0 / Predefine.MAX_FREQUENCE;
//-log{a*P(Ci-1)+(1-a)P(Ci|Ci-1)} Note 0<a<1
dValue = -Math.Log(smoothPara * (1.0 + dCurFreqency) / (Predefine.MAX_FREQUENCE + 80000.0)
+ (1.0 - smoothPara) * ((1.0 - dTemp) * nTwoWordsFreq / (1.0 + dCurFreqency) +
dTemp));
//Unknown words: P(Wi|Ci);while known words:1
if (pCur.Content.nPOS < 0)
{
dValue += pCur.Content.nPOS;
}
//Get the position index of current word in the position map table
nCurWordIndex = Utility.BinarySearch(pCur.row * Predefine.MAX_SENTENCE_LEN + pCur.col, m_npWordPosMapTable);
nNextWordIndex = Utility.BinarySearch(pNextWords.row * Predefine.MAX_SENTENCE_LEN + pNextWords.col, m_npWordPosMapTable);
aBiWordNet.SetElement(nCurWordIndex, nNextWordIndex, new ChainContent(dValue, pCur.Content.nPOS, sTwoWords));
pNextWords = pNextWords.next; //Get next word
}
pCur = pCur.next;
}
return(aBiWordNet);
}
