public override float Score(IntTaggedWord iTW, int loc, string word, string featureSpec)
{
int wordId = iTW.Word();
int tagId = iTW.Tag();
// Force 1-best path to go through the boundary symbol
// (deterministic tagging)
int boundaryId = wordIndex.IndexOf(LexiconConstants.Boundary);
int boundaryTagId = tagIndex.IndexOf(LexiconConstants.BoundaryTag);
if (wordId == boundaryId && tagId == boundaryTagId)
{
return(0.0f);
}
// Morphological features
string tag = tagIndex.Get(iTW.Tag());
Pair <string, string> lemmaMorph = MorphoFeatureSpecification.SplitMorphString(word, featureSpec);
string lemma = lemmaMorph.First();
int lemmaId = wordIndex.IndexOf(lemma);
string richMorphTag = lemmaMorph.Second();
string reducedMorphTag = morphoSpec.StrToFeatures(richMorphTag).ToString().Trim();
reducedMorphTag = reducedMorphTag.Length == 0 ? NoMorphAnalysis : reducedMorphTag;
int morphId = morphIndex.AddToIndex(reducedMorphTag);
// Score the factors and create the rule score p_W_T
double p_W_Tf = Math.Log(ProbWordTag(word, loc, wordId, tagId));
// double p_L_T = Math.log(probLemmaTag(word, loc, tagId, lemmaId));
double p_L_T = 0.0;
double p_M_T = Math.Log(ProbMorphTag(tagId, morphId));
double p_W_T = p_W_Tf + p_L_T + p_M_T;
// String tag = tagIndex.get(tagId);
// Filter low probability taggings
return(p_W_T > -100.0 ? (float)p_W_T : float.NegativeInfinity);
}
public override Tree TransformTree(Tree t, Tree root)
{
// Perform tregex-powered annotations
t = base.TransformTree(t, root);
string cat = t.Value();
//Add morphosyntactic features if this is a POS tag
if (t.IsPreTerminal() && tagSpec != null)
{
if (!(t.FirstChild().Label() is CoreLabel) || ((CoreLabel)t.FirstChild().Label()).OriginalText() == null)
{
throw new Exception(string.Format("%s: Term lacks morpho analysis: %s", this.GetType().FullName, t.ToString()));
}
string morphoStr = ((CoreLabel)t.FirstChild().Label()).OriginalText();
Pair <string, string> lemmaMorph = MorphoFeatureSpecification.SplitMorphString(string.Empty, morphoStr);
MorphoFeatures feats = tagSpec.StrToFeatures(lemmaMorph.Second());
cat = feats.GetTag(cat);
}
//Update the label(s)
t.SetValue(cat);
if (t.IsPreTerminal() && t.Label() is IHasTag)
{
((IHasTag)t.Label()).SetTag(cat);
}
return(t);
}
private static void ReplacePOSTag(Tree t, MorphoFeatureSpecification morpho)
{
if (!t.IsPreTerminal())
{
throw new ArgumentException("Can only operate on preterminals");
}
if (!(t.Label() is CoreLabel))
{
throw new ArgumentException("Only operates on CoreLabels");
}
CoreLabel label = (CoreLabel)t.Label();
Tree child = t.Children()[0];
if (!(child.Label() is CoreLabel))
{
throw new ArgumentException("Only operates on CoreLabels");
}
CoreLabel childLabel = (CoreLabel)child.Label();
// Morphological Analysis
string morphStr = childLabel.OriginalText();
if (morphStr == null || morphStr.Equals(string.Empty))
{
morphStr = label.Value();
// POS subcategory
string subCat = childLabel.Category();
if (subCat != null && subCat != string.Empty)
{
morphStr += "-" + subCat + "--";
}
else
{
morphStr += "---";
}
}
MorphoFeatures feats = morpho.StrToFeatures(morphStr);
if (feats.GetAltTag() != null && !feats.GetAltTag().Equals(string.Empty))
{
label.SetValue(feats.GetAltTag());
label.SetTag(feats.GetAltTag());
}
}
/// <summary>First map to the LDC short tags.</summary>
/// <remarks>
/// First map to the LDC short tags. Then map to the Universal POS. Then add
/// morphological annotations.
/// </remarks>
public override string Map(string posTag, string terminal)
{
string rawTag = posTag.Trim();
string shortTag = tagsToEscape.Contains(rawTag) ? rawTag : tagMap[rawTag];
if (shortTag == null)
{
System.Console.Error.Printf("%s: No LDC shortened tag for %s%n", this.GetType().FullName, rawTag);
return(rawTag);
}
string universalTag = universalMap[shortTag];
if (!universalMap.Contains(shortTag))
{
System.Console.Error.Printf("%s: No universal tag for LDC tag %s%n", this.GetType().FullName, shortTag);
universalTag = shortTag;
}
MorphoFeatures feats = new MorphoFeatures(morphoSpec.StrToFeatures(rawTag));
string functionalTag = feats.GetTag(universalTag);
return(functionalTag);
}
// private static String stripTag(String tag) {
// if (tag.startsWith("DT")) {
// String newTag = tag.substring(2, tag.length());
// return newTag.length() > 0 ? newTag : tag;
// }
// return tag;
// }
/// <param name="args"/>
public static void Main(string[] args)
{
if (args.Length != 3)
{
System.Console.Error.Printf("Usage: java %s language filename features%n", typeof(TreebankFactoredLexiconStats).FullName);
System.Environment.Exit(-1);
}
Language language = Language.ValueOf(args[0]);
ITreebankLangParserParams tlpp = language.@params;
if (language.Equals(Language.Arabic))
{
string[] options = new string[] { "-arabicFactored" };
tlpp.SetOptionFlag(options, 0);
}
else
{
string[] options = new string[] { "-frenchFactored" };
tlpp.SetOptionFlag(options, 0);
}
Treebank tb = tlpp.DiskTreebank();
tb.LoadPath(args[1]);
MorphoFeatureSpecification morphoSpec = language.Equals(Language.Arabic) ? new ArabicMorphoFeatureSpecification() : new FrenchMorphoFeatureSpecification();
string[] features = args[2].Trim().Split(",");
foreach (string feature in features)
{
morphoSpec.Activate(MorphoFeatureSpecification.MorphoFeatureType.ValueOf(feature));
}
// Counters
ICounter <string> wordTagCounter = new ClassicCounter <string>(30000);
ICounter <string> morphTagCounter = new ClassicCounter <string>(500);
// Counter<String> signatureTagCounter = new ClassicCounter<String>();
ICounter <string> morphCounter = new ClassicCounter <string>(500);
ICounter <string> wordCounter = new ClassicCounter <string>(30000);
ICounter <string> tagCounter = new ClassicCounter <string>(300);
ICounter <string> lemmaCounter = new ClassicCounter <string>(25000);
ICounter <string> lemmaTagCounter = new ClassicCounter <string>(25000);
ICounter <string> richTagCounter = new ClassicCounter <string>(1000);
ICounter <string> reducedTagCounter = new ClassicCounter <string>(500);
ICounter <string> reducedTagLemmaCounter = new ClassicCounter <string>(500);
IDictionary <string, ICollection <string> > wordLemmaMap = Generics.NewHashMap();
TwoDimensionalIntCounter <string, string> lemmaReducedTagCounter = new TwoDimensionalIntCounter <string, string>(30000);
TwoDimensionalIntCounter <string, string> reducedTagTagCounter = new TwoDimensionalIntCounter <string, string>(500);
TwoDimensionalIntCounter <string, string> tagReducedTagCounter = new TwoDimensionalIntCounter <string, string>(300);
int numTrees = 0;
foreach (Tree tree in tb)
{
foreach (Tree subTree in tree)
{
if (!subTree.IsLeaf())
{
tlpp.TransformTree(subTree, tree);
}
}
IList <ILabel> pretermList = tree.PreTerminalYield();
IList <ILabel> yield = tree.Yield();
System.Diagnostics.Debug.Assert(yield.Count == pretermList.Count);
int yieldLen = yield.Count;
for (int i = 0; i < yieldLen; ++i)
{
string tag = pretermList[i].Value();
string word = yield[i].Value();
string morph = ((CoreLabel)yield[i]).OriginalText();
// Note: if there is no lemma, then we use the surface form.
Pair <string, string> lemmaTag = MorphoFeatureSpecification.SplitMorphString(word, morph);
string lemma = lemmaTag.First();
string richTag = lemmaTag.Second();
// WSGDEBUG
if (tag.Contains("MW"))
{
lemma += "-MWE";
}
lemmaCounter.IncrementCount(lemma);
lemmaTagCounter.IncrementCount(lemma + tag);
richTagCounter.IncrementCount(richTag);
string reducedTag = morphoSpec.StrToFeatures(richTag).ToString();
reducedTagCounter.IncrementCount(reducedTag);
reducedTagLemmaCounter.IncrementCount(reducedTag + lemma);
wordTagCounter.IncrementCount(word + tag);
morphTagCounter.IncrementCount(morph + tag);
morphCounter.IncrementCount(morph);
wordCounter.IncrementCount(word);
tagCounter.IncrementCount(tag);
reducedTag = reducedTag.Equals(string.Empty) ? "NONE" : reducedTag;
if (wordLemmaMap.Contains(word))
{
wordLemmaMap[word].Add(lemma);
}
else
{
ICollection <string> lemmas = Generics.NewHashSet(1);
wordLemmaMap[word] = lemmas;
}
lemmaReducedTagCounter.IncrementCount(lemma, reducedTag);
reducedTagTagCounter.IncrementCount(lemma + reducedTag, tag);
tagReducedTagCounter.IncrementCount(tag, reducedTag);
}
++numTrees;
}
// Barf...
System.Console.Out.WriteLine("Language: " + language.ToString());
System.Console.Out.Printf("#trees:\t%d%n", numTrees);
System.Console.Out.Printf("#tokens:\t%d%n", (int)wordCounter.TotalCount());
System.Console.Out.Printf("#words:\t%d%n", wordCounter.KeySet().Count);
System.Console.Out.Printf("#tags:\t%d%n", tagCounter.KeySet().Count);
System.Console.Out.Printf("#wordTagPairs:\t%d%n", wordTagCounter.KeySet().Count);
System.Console.Out.Printf("#lemmas:\t%d%n", lemmaCounter.KeySet().Count);
System.Console.Out.Printf("#lemmaTagPairs:\t%d%n", lemmaTagCounter.KeySet().Count);
System.Console.Out.Printf("#feattags:\t%d%n", reducedTagCounter.KeySet().Count);
System.Console.Out.Printf("#feattag+lemmas:\t%d%n", reducedTagLemmaCounter.KeySet().Count);
System.Console.Out.Printf("#richtags:\t%d%n", richTagCounter.KeySet().Count);
System.Console.Out.Printf("#richtag+lemma:\t%d%n", morphCounter.KeySet().Count);
System.Console.Out.Printf("#richtag+lemmaTagPairs:\t%d%n", morphTagCounter.KeySet().Count);
// Extra
System.Console.Out.WriteLine("==================");
StringBuilder sbNoLemma = new StringBuilder();
StringBuilder sbMultLemmas = new StringBuilder();
foreach (KeyValuePair <string, ICollection <string> > wordLemmas in wordLemmaMap)
{
string word = wordLemmas.Key;
ICollection <string> lemmas = wordLemmas.Value;
if (lemmas.Count == 0)
{
sbNoLemma.Append("NO LEMMAS FOR WORD: " + word + "\n");
continue;
}
if (lemmas.Count > 1)
{
sbMultLemmas.Append("MULTIPLE LEMMAS: " + word + " " + SetToString(lemmas) + "\n");
continue;
}
string lemma = lemmas.GetEnumerator().Current;
ICollection <string> reducedTags = lemmaReducedTagCounter.GetCounter(lemma).KeySet();
if (reducedTags.Count > 1)
{
System.Console.Out.Printf("%s --> %s%n", word, lemma);
foreach (string reducedTag in reducedTags)
{
int count = lemmaReducedTagCounter.GetCount(lemma, reducedTag);
string posTags = SetToString(reducedTagTagCounter.GetCounter(lemma + reducedTag).KeySet());
System.Console.Out.Printf("\t%s\t%d\t%s%n", reducedTag, count, posTags);
}
System.Console.Out.WriteLine();
}
}
System.Console.Out.WriteLine("==================");
System.Console.Out.WriteLine(sbNoLemma.ToString());
System.Console.Out.WriteLine(sbMultLemmas.ToString());
System.Console.Out.WriteLine("==================");
IList <string> tags = new List <string>(tagReducedTagCounter.FirstKeySet());
tags.Sort();
foreach (string tag_1 in tags)
{
System.Console.Out.WriteLine(tag_1);
ICollection <string> reducedTags = tagReducedTagCounter.GetCounter(tag_1).KeySet();
foreach (string reducedTag in reducedTags)
{
int count = tagReducedTagCounter.GetCount(tag_1, reducedTag);
// reducedTag = reducedTag.equals("") ? "NONE" : reducedTag;
System.Console.Out.Printf("\t%s\t%d%n", reducedTag, count);
}
System.Console.Out.WriteLine();
}
System.Console.Out.WriteLine("==================");
}