public override void Train(TaggedWord tw, int loc, double weight)
{
if (useGT)
{
unknownGTTrainer.Train(tw, weight);
}
// scan data
string word = tw.Word();
string subString = model.GetSignature(word, loc);
ILabel tag = new Tag(tw.Tag());
if (!c.Contains(tag))
{
c[tag] = new ClassicCounter <string>();
}
c[tag].IncrementCount(subString, weight);
tc.IncrementCount(tag, weight);
seenEnd.Add(subString);
string tagStr = tw.Tag();
IntTaggedWord iW = new IntTaggedWord(word, IntTaggedWord.Any, wordIndex, tagIndex);
seenCounter.IncrementCount(iW, weight);
if (treesRead > indexToStartUnkCounting)
{
// start doing this once some way through trees;
// treesRead is 1 based counting
if (seenCounter.GetCount(iW) < 2)
{
IntTaggedWord iT = new IntTaggedWord(IntTaggedWord.Any, tagStr, wordIndex, tagIndex);
unSeenCounter.IncrementCount(iT, weight);
unSeenCounter.IncrementCount(UnknownWordModelTrainerConstants.NullItw, weight);
}
}
}
/// <summary>Trains the first-character based unknown word model.</summary>
/// <param name="tw">The word we are currently training on</param>
/// <param name="loc">The position of that word</param>
/// <param name="weight">The weight to give this word in terms of training</param>
public override void Train(TaggedWord tw, int loc, double weight)
{
if (useGT)
{
unknownGTTrainer.Train(tw, weight);
}
string word = tw.Word();
ILabel tagL = new Tag(tw.Tag());
string first = Sharpen.Runtime.Substring(word, 0, 1);
if (useUnicodeType)
{
char ch = word[0];
int type = char.GetType(ch);
if (type != char.OtherLetter)
{
// standard Chinese characters are of type "OTHER_LETTER"!!
first = int.ToString(type);
}
}
string tag = tw.Tag();
if (!c.Contains(tagL))
{
c[tagL] = new ClassicCounter <string>();
}
c[tagL].IncrementCount(first, weight);
tc.IncrementCount(tagL, weight);
seenFirst.Add(first);
IntTaggedWord iW = new IntTaggedWord(word, IntTaggedWord.Any, wordIndex, tagIndex);
seenCounter.IncrementCount(iW, weight);
if (treesRead > indexToStartUnkCounting)
{
// start doing this once some way through trees;
// treesRead is 1 based counting
if (seenCounter.GetCount(iW) < 2)
{
IntTaggedWord iT = new IntTaggedWord(IntTaggedWord.Any, tag, wordIndex, tagIndex);
unSeenCounter.IncrementCount(iT, weight);
unSeenCounter.IncrementCount(iTotal, weight);
}
}
}
