/// <summary>
/// Attempt to infer the part of speech of the given preterminal node, which
/// was created during the expansion of a multi-word token.
/// </summary>
private static string InferPOS(Tree t, Tree parent, TwoDimensionalCounter <string, string> unigramTagger)
{
string word = t.FirstChild().Value();
string containingPhraseStr = GetContainingPhrase(t, parent);
// Overrides: let the manual POS model handle a few special cases first
string overrideTag = MultiWordPreprocessor.ManualUWModel.GetOverrideTag(word, containingPhraseStr);
if (overrideTag != null)
{
return(overrideTag);
}
ICollection <string> unigramTaggerKeys = unigramTagger.FirstKeySet();
// Try treating this word as a verb and stripping any clitic
// pronouns. If the stripped version exists in the unigram
// tagger, then stick with the verb hypothesis
SpanishVerbStripper.StrippedVerb strippedVerb = verbStripper.SeparatePronouns(word);
if (strippedVerb != null && unigramTaggerKeys.Contains(strippedVerb.GetStem()))
{
string pos = Counters.Argmax(unigramTagger.GetCounter(strippedVerb.GetStem()));
if (pos.StartsWith("v"))
{
return(pos);
}
}
if (unigramTagger.FirstKeySet().Contains(word))
{
return(Counters.Argmax(unigramTagger.GetCounter(word), new MultiWordPreprocessor.POSTieBreaker()));
}
return(MultiWordPreprocessor.ManualUWModel.GetTag(word, containingPhraseStr));
}
private double NumNonRedundantPatterns(TwoDimensionalCounter <CandidatePhrase, E> terms, CandidatePhrase w)
{
object[] pats = Sharpen.Collections.ToArray(terms.GetCounter(w).KeySet());
int numPat = 0;
for (int i = 0; i < pats.Length; i++)
{
//String pati = constVars.getPatternIndex().get(pats[i]).toString();
string pati = pats[i].ToString();
bool contains = false;
for (int j = i + 1; j < pats.Length; j++)
{
//String patj = constVars.getPatternIndex().get(pats[j]).toString();
string patj = pats[j].ToString();
if (patj.Contains(pati) || pati.Contains(patj))
{
contains = true;
break;
}
}
if (!contains)
{
numPat++;
}
}
return(numPat);
}
private static void CountTaggings(Treebank tb, PrintWriter pw)
{
TwoDimensionalCounter <string, string> wtc = new TwoDimensionalCounter <string, string>();
tb.Apply(null);
foreach (string key in wtc.FirstKeySet())
{
pw.Print(key);
pw.Print('\t');
ICounter <string> ctr = wtc.GetCounter(key);
foreach (string k2 in ctr.KeySet())
{
pw.Print(k2 + '\t' + ctr.GetCount(k2) + '\t');
}
pw.Println();
}
}
public static void TraverseAndFix(Tree t, TwoDimensionalCounter <string, string> pretermLabel, TwoDimensionalCounter <string, string> unigramTagger)
{
if (t.IsPreTerminal())
{
if (t.Value().Equals(FrenchXMLTreeReader.MissingPos))
{
nMissingPOS++;
string word = t.FirstChild().Value();
string tag = (unigramTagger.FirstKeySet().Contains(word)) ? Counters.Argmax(unigramTagger.GetCounter(word)) : MWEPreprocessor.ManualUWModel.GetTag(word);
t.SetValue(tag);
}
return;
}
foreach (Tree kid in t.Children())
{
TraverseAndFix(kid, pretermLabel, unigramTagger);
}
//Post-order visit
if (t.Value().Equals(FrenchXMLTreeReader.MissingPhrasal))
{
nMissingPhrasal++;
StringBuilder sb = new StringBuilder();
foreach (Tree kid_1 in t.Children())
{
sb.Append(kid_1.Value()).Append(" ");
}
string posSequence = sb.ToString().Trim();
if (pretermLabel.FirstKeySet().Contains(posSequence))
{
string phrasalCat = Counters.Argmax(pretermLabel.GetCounter(posSequence));
t.SetValue(phrasalCat);
}
else
{
System.Console.Out.WriteLine("No phrasal cat for: " + posSequence);
}
}
}
public static void PrintCounter(TwoDimensionalCounter <string, string> cnt, string fname)
{
try
{
PrintWriter pw = new PrintWriter(new TextWriter(new FileOutputStream(new File(fname)), false, "UTF-8"));
foreach (string key in cnt.FirstKeySet())
{
foreach (string val in cnt.GetCounter(key).KeySet())
{
pw.Printf("%s\t%s\t%d%n", key, val, (int)cnt.GetCount(key, val));
}
}
pw.Close();
}
catch (UnsupportedEncodingException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
catch (FileNotFoundException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
private ICounter <CandidatePhrase> LearnNewPhrasesPrivate(string label, PatternsForEachToken patternsForEachToken, ICounter <E> patternsLearnedThisIter, ICounter <E> allSelectedPatterns, ICollection <CandidatePhrase> alreadyIdentifiedWords, CollectionValuedMap
<E, Triple <string, int, int> > matchedTokensByPat, ICounter <CandidatePhrase> scoreForAllWordsThisIteration, TwoDimensionalCounter <CandidatePhrase, E> terms, TwoDimensionalCounter <CandidatePhrase, E> wordsPatExtracted, TwoDimensionalCounter <E
, CandidatePhrase> patternsAndWords4Label, string identifier, ICollection <CandidatePhrase> ignoreWords, bool computeProcDataFreq)
{
ICollection <CandidatePhrase> alreadyLabeledWords = new HashSet <CandidatePhrase>();
if (constVars.doNotApplyPatterns)
{
// if want to get the stats by the lossy way of just counting without
// applying the patterns
ConstantsAndVariables.DataSentsIterator sentsIter = new ConstantsAndVariables.DataSentsIterator(constVars.batchProcessSents);
while (sentsIter.MoveNext())
{
Pair <IDictionary <string, DataInstance>, File> sentsf = sentsIter.Current;
this.StatsWithoutApplyingPatterns(sentsf.First(), patternsForEachToken, patternsLearnedThisIter, wordsPatExtracted);
}
}
else
{
if (patternsLearnedThisIter.Size() > 0)
{
this.ApplyPats(patternsLearnedThisIter, label, wordsPatExtracted, matchedTokensByPat, alreadyLabeledWords);
}
}
if (computeProcDataFreq)
{
if (!phraseScorer.wordFreqNorm.Equals(PhraseScorer.Normalization.None))
{
Redwood.Log(Redwood.Dbg, "computing processed freq");
foreach (KeyValuePair <CandidatePhrase, double> fq in Data.rawFreq.EntrySet())
{
double @in = fq.Value;
if (phraseScorer.wordFreqNorm.Equals(PhraseScorer.Normalization.Sqrt))
{
@in = Math.Sqrt(@in);
}
else
{
if (phraseScorer.wordFreqNorm.Equals(PhraseScorer.Normalization.Log))
{
@in = 1 + Math.Log(@in);
}
else
{
throw new Exception("can't understand the normalization");
}
}
System.Diagnostics.Debug.Assert(!double.IsNaN(@in), "Why is processed freq nan when rawfreq is " + @in);
Data.processedDataFreq.SetCount(fq.Key, @in);
}
}
else
{
Data.processedDataFreq = Data.rawFreq;
}
}
if (constVars.wordScoring.Equals(GetPatternsFromDataMultiClass.WordScoring.Weightednorm))
{
foreach (CandidatePhrase en in wordsPatExtracted.FirstKeySet())
{
if (!constVars.GetOtherSemanticClassesWords().Contains(en) && (en.GetPhraseLemma() == null || !constVars.GetOtherSemanticClassesWords().Contains(CandidatePhrase.CreateOrGet(en.GetPhraseLemma()))) && !alreadyLabeledWords.Contains(en))
{
terms.AddAll(en, wordsPatExtracted.GetCounter(en));
}
}
RemoveKeys(terms, ConstantsAndVariables.GetStopWords());
ICounter <CandidatePhrase> phraseScores = phraseScorer.ScorePhrases(label, terms, wordsPatExtracted, allSelectedPatterns, alreadyIdentifiedWords, false);
System.Console.Out.WriteLine("count for word U.S. is " + phraseScores.GetCount(CandidatePhrase.CreateOrGet("U.S.")));
ICollection <CandidatePhrase> ignoreWordsAll;
if (ignoreWords != null && !ignoreWords.IsEmpty())
{
ignoreWordsAll = CollectionUtils.UnionAsSet(ignoreWords, constVars.GetOtherSemanticClassesWords());
}
else
{
ignoreWordsAll = new HashSet <CandidatePhrase>(constVars.GetOtherSemanticClassesWords());
}
Sharpen.Collections.AddAll(ignoreWordsAll, constVars.GetSeedLabelDictionary()[label]);
Sharpen.Collections.AddAll(ignoreWordsAll, constVars.GetLearnedWords(label).KeySet());
System.Console.Out.WriteLine("ignoreWordsAll contains word U.S. is " + ignoreWordsAll.Contains(CandidatePhrase.CreateOrGet("U.S.")));
ICounter <CandidatePhrase> finalwords = ChooseTopWords(phraseScores, terms, phraseScores, ignoreWordsAll, constVars.thresholdWordExtract);
phraseScorer.PrintReasonForChoosing(finalwords);
scoreForAllWordsThisIteration.Clear();
Counters.AddInPlace(scoreForAllWordsThisIteration, phraseScores);
Redwood.Log(ConstantsAndVariables.minimaldebug, "\n\n## Selected Words for " + label + " : " + Counters.ToSortedString(finalwords, finalwords.Size(), "%1$s:%2$.2f", "\t"));
if (constVars.goldEntities != null)
{
IDictionary <string, bool> goldEntities4Label = constVars.goldEntities[label];
if (goldEntities4Label != null)
{
StringBuilder s = new StringBuilder();
finalwords.KeySet().Stream().ForEach(null);
Redwood.Log(ConstantsAndVariables.minimaldebug, "\n\n## Gold labels for selected words for label " + label + " : " + s.ToString());
}
else
{
Redwood.Log(Redwood.Dbg, "No gold entities provided for label " + label);
}
}
if (constVars.outDir != null && !constVars.outDir.IsEmpty())
{
string outputdir = constVars.outDir + "/" + identifier + "/" + label;
IOUtils.EnsureDir(new File(outputdir));
TwoDimensionalCounter <CandidatePhrase, CandidatePhrase> reasonForWords = new TwoDimensionalCounter <CandidatePhrase, CandidatePhrase>();
foreach (CandidatePhrase word in finalwords.KeySet())
{
foreach (E l in wordsPatExtracted.GetCounter(word).KeySet())
{
foreach (CandidatePhrase w2 in patternsAndWords4Label.GetCounter(l))
{
reasonForWords.IncrementCount(word, w2);
}
}
}
Redwood.Log(ConstantsAndVariables.minimaldebug, "Saving output in " + outputdir);
string filename = outputdir + "/words.json";
// the json object is an array corresponding to each iteration - of list
// of objects,
// each of which is a bean of entity and reasons
IJsonArrayBuilder obj = Javax.Json.Json.CreateArrayBuilder();
if (writtenInJustification.Contains(label) && writtenInJustification[label])
{
IJsonReader jsonReader = Javax.Json.Json.CreateReader(new BufferedInputStream(new FileInputStream(filename)));
IJsonArray objarr = jsonReader.ReadArray();
foreach (IJsonValue o in objarr)
{
obj.Add(o);
}
jsonReader.Close();
}
IJsonArrayBuilder objThisIter = Javax.Json.Json.CreateArrayBuilder();
foreach (CandidatePhrase w in reasonForWords.FirstKeySet())
{
IJsonObjectBuilder objinner = Javax.Json.Json.CreateObjectBuilder();
IJsonArrayBuilder l = Javax.Json.Json.CreateArrayBuilder();
foreach (CandidatePhrase w2 in reasonForWords.GetCounter(w).KeySet())
{
l.Add(w2.GetPhrase());
}
IJsonArrayBuilder pats = Javax.Json.Json.CreateArrayBuilder();
foreach (E p in wordsPatExtracted.GetCounter(w))
{
pats.Add(p.ToStringSimple());
}
objinner.Add("reasonwords", l);
objinner.Add("patterns", pats);
objinner.Add("score", finalwords.GetCount(w));
objinner.Add("entity", w.GetPhrase());
objThisIter.Add(objinner.Build());
}
obj.Add(objThisIter);
// Redwood.log(ConstantsAndVariables.minimaldebug, channelNameLogger,
// "Writing justification at " + filename);
IOUtils.WriteStringToFile(StringUtils.Normalize(StringUtils.ToAscii(obj.Build().ToString())), filename, "ASCII");
writtenInJustification[label] = true;
}
if (constVars.justify)
{
Redwood.Log(Redwood.Dbg, "\nJustification for phrases:\n");
foreach (CandidatePhrase word in finalwords.KeySet())
{
Redwood.Log(Redwood.Dbg, "Phrase " + word + " extracted because of patterns: \t" + Counters.ToSortedString(wordsPatExtracted.GetCounter(word), wordsPatExtracted.GetCounter(word).Size(), "%1$s:%2$f", "\n"));
}
}
// if (usePatternResultAsLabel)
// if (answerLabel != null)
// labelWords(sents, commonEngWords, finalwords.keySet(),
// patterns.keySet(), outFile);
// else
// throw new RuntimeException("why is the answer label null?");
return(finalwords);
}
else
{
if (constVars.wordScoring.Equals(GetPatternsFromDataMultiClass.WordScoring.Bpb))
{
Counters.AddInPlace(terms, wordsPatExtracted);
ICounter <CandidatePhrase> maxPatWeightTerms = new ClassicCounter <CandidatePhrase>();
IDictionary <CandidatePhrase, E> wordMaxPat = new Dictionary <CandidatePhrase, E>();
foreach (KeyValuePair <CandidatePhrase, ClassicCounter <E> > en in terms.EntrySet())
{
ICounter <E> weights = new ClassicCounter <E>();
foreach (E k in en.Value.KeySet())
{
weights.SetCount(k, patternsLearnedThisIter.GetCount(k));
}
maxPatWeightTerms.SetCount(en.Key, Counters.Max(weights));
wordMaxPat[en.Key] = Counters.Argmax(weights);
}
Counters.RemoveKeys(maxPatWeightTerms, alreadyIdentifiedWords);
double maxvalue = Counters.Max(maxPatWeightTerms);
ICollection <CandidatePhrase> words = Counters.KeysAbove(maxPatWeightTerms, maxvalue - 1e-10);
CandidatePhrase bestw = null;
if (words.Count > 1)
{
double max = double.NegativeInfinity;
foreach (CandidatePhrase w in words)
{
if (terms.GetCount(w, wordMaxPat[w]) > max)
{
max = terms.GetCount(w, wordMaxPat[w]);
bestw = w;
}
}
}
else
{
if (words.Count == 1)
{
bestw = words.GetEnumerator().Current;
}
else
{
return(new ClassicCounter <CandidatePhrase>());
}
}
Redwood.Log(ConstantsAndVariables.minimaldebug, "Selected Words: " + bestw);
return(Counters.AsCounter(Arrays.AsList(bestw)));
}
else
{
throw new Exception("wordscoring " + constVars.wordScoring + " not identified");
}
}
}
public virtual ICounter <CandidatePhrase> ChooseTopWords(ICounter <CandidatePhrase> newdt, TwoDimensionalCounter <CandidatePhrase, E> terms, ICounter <CandidatePhrase> useThresholdNumPatternsForTheseWords, ICollection <CandidatePhrase> ignoreWords
, double thresholdWordExtract)
{
IEnumerator <CandidatePhrase> termIter = Counters.ToPriorityQueue(newdt).GetEnumerator();
ICounter <CandidatePhrase> finalwords = new ClassicCounter <CandidatePhrase>();
while (termIter.MoveNext())
{
if (finalwords.Size() >= constVars.numWordsToAdd)
{
break;
}
CandidatePhrase w = termIter.Current;
if (newdt.GetCount(w) < thresholdWordExtract)
{
Redwood.Log(ConstantsAndVariables.extremedebug, "not adding word " + w + " and any later words because the score " + newdt.GetCount(w) + " is less than the threshold of " + thresholdWordExtract);
break;
}
System.Diagnostics.Debug.Assert((newdt.GetCount(w) != double.PositiveInfinity));
if (useThresholdNumPatternsForTheseWords.ContainsKey(w) && NumNonRedundantPatterns(terms, w) < constVars.thresholdNumPatternsApplied)
{
Redwood.Log("extremePatDebug", "Not adding " + w + " because the number of non redundant patterns are below threshold of " + constVars.thresholdNumPatternsApplied + ":" + terms.GetCounter(w).KeySet());
continue;
}
CandidatePhrase matchedFuzzy = null;
if (constVars.minLen4FuzzyForPattern > 0 && ignoreWords != null)
{
matchedFuzzy = ConstantsAndVariables.ContainsFuzzy(ignoreWords, w, constVars.minLen4FuzzyForPattern);
}
if (matchedFuzzy == null)
{
Redwood.Log("extremePatDebug", "adding word " + w);
finalwords.SetCount(w, newdt.GetCount(w));
}
else
{
Redwood.Log("extremePatDebug", "not adding " + w + " because it matched " + matchedFuzzy + " in common English word");
ignoreWords.Add(w);
}
}
string nextTen = string.Empty;
int n = 0;
while (termIter.MoveNext())
{
n++;
if (n > 10)
{
break;
}
CandidatePhrase w = termIter.Current;
nextTen += ";\t" + w + ":" + newdt.GetCount(w);
}
Redwood.Log(Redwood.Dbg, "Next ten phrases were " + nextTen);
return(finalwords);
}
public static void Main(string[] args)
{
if (args.Length != 1)
{
System.Console.Error.Printf("Usage: java %s file%n", typeof(Edu.Stanford.Nlp.International.French.Scripts.MWEFrequencyDist).FullName);
System.Environment.Exit(-1);
}
File treeFile = new File(args[0]);
TwoDimensionalCounter <string, string> mweLabelToString = new TwoDimensionalCounter <string, string>();
ICollection <string> uniquePOSSequences = Generics.NewHashSet();
try
{
BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
ITreeReaderFactory trf = new FrenchTreeReaderFactory();
ITreeReader tr = trf.NewTreeReader(br);
TregexPattern pMWE = TregexPattern.Compile("/^MW/");
for (Tree t; (t = tr.ReadTree()) != null;)
{
//Count MWE statistics
TregexMatcher m = pMWE.Matcher(t);
while (m.FindNextMatchingNode())
{
Tree match = m.GetMatch();
string label = match.Value();
IList <CoreLabel> yield = match.TaggedLabeledYield();
StringBuilder termYield = new StringBuilder();
StringBuilder posYield = new StringBuilder();
foreach (CoreLabel cl in yield)
{
termYield.Append(cl.Word()).Append(" ");
posYield.Append(cl.Tag()).Append(" ");
}
mweLabelToString.IncrementCount(label, termYield.ToString().Trim());
uniquePOSSequences.Add(posYield.ToString().Trim());
}
}
tr.Close();
//Closes the underlying reader
System.Console.Out.Printf("Type\t#Type\t#Single\t%%Single\t%%Total%n");
double nMWEs = mweLabelToString.TotalCount();
int nAllSingletons = 0;
int nTokens = 0;
foreach (string mweLabel in mweLabelToString.FirstKeySet())
{
int nSingletons = 0;
double totalCount = mweLabelToString.TotalCount(mweLabel);
ICounter <string> mc = mweLabelToString.GetCounter(mweLabel);
foreach (string term in mc.KeySet())
{
if (mc.GetCount(term) == 1.0)
{
nSingletons++;
}
nTokens += term.Split("\\s+").Length *(int)mc.GetCount(term);
}
nAllSingletons += nSingletons;
System.Console.Out.Printf("%s\t%d\t%d\t%.2f\t%.2f%n", mweLabel, (int)totalCount, nSingletons, 100.0 * nSingletons / totalCount, 100.0 * totalCount / nMWEs);
}
System.Console.Out.Printf("TOTAL:\t%d\t%d\t%.2f%n", (int)nMWEs, nAllSingletons, 100.0 * nAllSingletons / nMWEs);
System.Console.Out.WriteLine("#tokens = " + nTokens);
System.Console.Out.WriteLine("#unique MWE POS sequences = " + uniquePOSSequences.Count);
}
catch (UnsupportedEncodingException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
catch (FileNotFoundException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
catch (TregexParseException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
catch (IOException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
}
