/**
* Reads the probability table from the given DataInputStream.
*
* @param stream the DataInputStream from which to read the table
* @param bigEndian true if the given stream is bigEndian, false otherwise
* @throws java.io.IOException
*/
private float[] ReadFloatTable(Stream stream, Boolean bigEndian)
{
var numProbs = ReadInt(stream, bigEndian);
if (numProbs <= 0 || numProbs > MaxProbTableSize)
{
throw new Exception("Bad probabilities table size: " + numProbs);
}
var probTable = new float[numProbs];
for (var i = 0; i < numProbs; i++)
{
//probTable[i] = readFloat(stream, bigEndian);
probTable[i] = _logMath.Log10ToLog(ReadFloat(stream, bigEndian));
}
return(probTable);
}
/// <summary>
/// Loads the language model from the given location.
/// </summary>
/// <param name="location">The URL location of the model.</param>
/// <param name="unigramWeightValue">The unigram weight.</param>
/// <param name="dictionaryValue">The dictionary.</param>
private void Load(URL location, float unigramWeightValue, IDictionary dictionaryValue)
{
string line;
float logUnigramWeight = _logMath.LinearToLog(unigramWeightValue);
float inverseLogUnigramWeight = _logMath
.LinearToLog(1.0 - unigramWeightValue);
Open(location);
// look for beginning of data
ReadUntil("\\data\\");
// look for ngram statements
List <int> ngramList = new List <int>();
while ((line = ReadLine()) != null)
{
if (line.StartsWith("ngram"))
{
StringTokenizer st = new StringTokenizer(line, " \t\n\r\f=");
if (st.countTokens() != 3)
{
Corrupt("corrupt ngram field " + line + ' '
+ st.countTokens());
}
st.nextToken();
int index = int.Parse(st.nextToken(), CultureInfo.InvariantCulture.NumberFormat);
int count = int.Parse(st.nextToken(), CultureInfo.InvariantCulture.NumberFormat);
ngramList.Insert(index - 1, count);
MaxDepth = Math.Max(index, MaxDepth);
}
else if (line.Equals("\\1-grams:"))
{
break;
}
}
int numUnigrams = ngramList[0] - 1;
// -log(x) = log(1/x)
float logUniformProbability = -_logMath.LinearToLog(numUnigrams);
for (int index = 0; index < ngramList.Count; index++)
{
int ngram = index + 1;
int ngramCount = ngramList[index];
for (int i = 0; i < ngramCount; i++)
{
StringTokenizer tok = new StringTokenizer(ReadLine());
int tokenCount = tok.countTokens();
if (tokenCount != ngram + 1 && tokenCount != ngram + 2)
{
Corrupt("Bad format");
}
float log10Prob = float.Parse(tok.nextToken(), CultureInfo.InvariantCulture.NumberFormat);
float log10Backoff = 0.0f;
// construct the WordSequence for this N-Gram
List <Word> wordList = new List <Word>(MaxDepth);
for (int j = 0; j < ngram; j++)
{
string word = tok.nextToken();
_vocabulary.Add(word);
Word wordObject = dictionaryValue.GetWord(word);
if (wordObject == null)
{
wordObject = Word.Unknown;
}
wordList.Add(wordObject);
}
WordSequence wordSequence = new WordSequence(wordList);
if (tok.hasMoreTokens())
{
log10Backoff = float.Parse(tok.nextToken(), CultureInfo.InvariantCulture.NumberFormat);
}
float logProb = _logMath.Log10ToLog(log10Prob);
float logBackoff = _logMath.Log10ToLog(log10Backoff);
// Apply unigram weights if this is a unigram probability
if (ngram == 1)
{
float p1 = logProb + logUnigramWeight;
float p2 = logUniformProbability + inverseLogUnigramWeight;
logProb = _logMath.AddAsLinear(p1, p2);
// System.out
// .println("p1 " + p1 + " p2 " + p2 + " luw "
// + logUnigramWeight + " iluw "
// + inverseLogUnigramWeight + " lup "
// + logUniformProbability + " logprog "
// + logProb);
}
Put(wordSequence, logProb, logBackoff);
}
if (index < ngramList.Count - 1)
{
string next = "\\" + (ngram + 1) + "-grams:";
ReadUntil(next);
}
}
ReadUntil("\\end\\");
Close();
}
