public ForwardBackwordAlgo(List<string> inputSentence, WeightVector wc, List<string> tagList)
{
_inputSentence = inputSentence;
_wc = wc;
_tagList = tagList;
_alphaDictionary = new Dictionary<int, Dictionary<string, double>>();
_betaDictionary = new Dictionary<int, Dictionary<string, double>>();
_uDictionary = new Dictionary<int, Dictionary<string, double>>();
UabDictionary = new Dictionary<int, Dictionary<string, double>>();
Z = 0;
_weightedFeaturesum = new WeightedFeatureSum(wc, inputSentence, true);
cList = new List<double>(_inputSentence.Count);
dList = new List<double>(_inputSentence.Count);
_useScaling = true;
_useLog = false;
_twoGramsList = new string[4];
var ngramTags = new Tags(_tagList);
int index = 0;
foreach (var ngram in ngramTags.GetNGramTags(2))
{
if (index >= _twoGramsList.Length)
{
Array.Resize(ref _twoGramsList, index + 1);
}
string[] split = ngram.Split(new[] { ':' });
_twoGramsList[index] = split[0] + "@#" + split[1];
index++;
}
}
public ComputeGradient(List<List<string>> inputSentence, List<List<string>> tagsList,
List<string> tagList, double lambda, double learningParam, FeatureCache cache, WriteModel logger)
{
Logger = logger;
_inputSentence = inputSentence;
_outputTagsList = tagsList;
_tagList = tagList;
_lambda = lambda;
_learningParam = learningParam;
_cache = cache;
forwardBackwordAlgos = new List<ForwardBackwordAlgo>();
_weightVector = null;
_twoGramsList = new string[4];
_twoGramPair = new KeyValuePair<string, string>[4];
var ngramTags = new Tags(_tagList);
int index = 0;
foreach (var ngram in ngramTags.GetNGramTags(2))
{
if (index >= _twoGramsList.Length)
{
Array.Resize(ref _twoGramsList, index+1);
Array.Resize(ref _twoGramPair, index + 1);
}
string[] split = ngram.Split(new[] { ':' });
_twoGramsList[index] = split[0] +"@#"+ split[1];
_twoGramPair[index] = new KeyValuePair<string, string>(split[0], split[1]);
index++;
}
}
public void CreateCache()
{
Console.WriteLine(DateTime.Now + "creating Cache begin");
var ngramTags = new Tags(_tags);
foreach (var ngramTag in ngramTags.GetNGramTags(2))
{
string[] split = ngramTag.Split(new[] { ':' });
for (var lineIndex = 0; lineIndex < Sentences.Count; lineIndex++)
{
for (var pos = 0; pos < Sentences[lineIndex].Count; pos++)
{
if (pos == 0)
{
StoreFeature("*", split[1], pos, lineIndex);
}
else
{
StoreFeature(split[0], split[1], pos, lineIndex);
}
}
}
}
Console.WriteLine(DateTime.Now + "creating Cache end");
}
private double GetSecondTerm(Tags ngramTags,
int lineIndex, int pos, int k)
{
double sum = 0;
foreach (var ngramTag in ngramTags.GetNGramTags(2))
{
string[] split = ngramTag.Split(new[] { ':' });
if (_cache.Contains(split[0], split[1], k, pos, lineIndex))
{
sum += (forwardBackwordAlgos[lineIndex].GetQ(pos, split[0], split[1]) *
_weightVector.Get(k));
}
//else
//{
// sum += (forwardBackwordAlgos[lineIndex].GetQ(j, split[0], split[1]) *
// weightedFeatureSum.GetFeatureK(split[0], split[1], j, k, sentence));
//}
}
return sum;
}
