private static IJsonArray GetSentenceArray(IList <CoreLabel> sentence)
{
IJsonArrayBuilder sentenceBuilder = Javax.Json.Json.CreateArrayBuilder();
sentence.Stream().Map(null).Map(null).Map(null).ForEach(null);
return(sentenceBuilder.Build());
}
public virtual string GetAllAnnotations(string input)
{
IJsonObjectBuilder objsent = Javax.Json.Json.CreateObjectBuilder();
int tokenid = 0;
foreach (CoreLabel l in Data.sents[input].GetTokens())
{
bool haslabel = false;
IJsonArrayBuilder labelArr = Javax.Json.Json.CreateArrayBuilder();
foreach (KeyValuePair <string, Type> en in this.humanLabelClasses)
{
if (!l.Get(en.Value).Equals(backgroundSymbol))
{
haslabel = true;
labelArr.Add(en.Key);
}
}
if (haslabel)
{
objsent.Add(tokenid.ToString(), labelArr);
}
tokenid++;
}
return(objsent.Build().ToString());
}
/// <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 void Process(int id, Document document)
{
IJsonArrayBuilder clusters = Javax.Json.Json.CreateArrayBuilder();
foreach (CorefCluster gold in document.goldCorefClusters.Values)
{
IJsonArrayBuilder c = Javax.Json.Json.CreateArrayBuilder();
foreach (Mention m in gold.corefMentions)
{
c.Add(m.mentionID);
}
clusters.Add(c.Build());
}
goldClusterWriter.Println(Javax.Json.Json.CreateObjectBuilder().Add(id.ToString(), clusters.Build()).Build());
IDictionary <Pair <int, int>, bool> mentionPairs = CorefUtils.GetLabeledMentionPairs(document);
IList <Mention> mentionsList = CorefUtils.GetSortedMentions(document);
IDictionary <int, IList <Mention> > mentionsByHeadIndex = new Dictionary <int, IList <Mention> >();
foreach (Mention m_1 in mentionsList)
{
IList <Mention> withIndex = mentionsByHeadIndex.ComputeIfAbsent(m_1.headIndex, null);
withIndex.Add(m_1);
}
IJsonObjectBuilder docFeatures = Javax.Json.Json.CreateObjectBuilder();
docFeatures.Add("doc_id", id);
docFeatures.Add("type", document.docType == Document.DocType.Article ? 1 : 0);
docFeatures.Add("source", document.docInfo["DOC_ID"].Split("/")[0]);
IJsonArrayBuilder sentences = Javax.Json.Json.CreateArrayBuilder();
foreach (ICoreMap sentence in document.annotation.Get(typeof(CoreAnnotations.SentencesAnnotation)))
{
sentences.Add(GetSentenceArray(sentence.Get(typeof(CoreAnnotations.TokensAnnotation))));
}
IJsonObjectBuilder mentions = Javax.Json.Json.CreateObjectBuilder();
foreach (Mention m_2 in document.predictedMentionsByID.Values)
{
IEnumerator <SemanticGraphEdge> iterator = m_2.enhancedDependency.IncomingEdgeIterator(m_2.headIndexedWord);
SemanticGraphEdge relation = iterator.MoveNext() ? iterator.Current : null;
string depRelation = relation == null ? "no-parent" : relation.GetRelation().ToString();
string depParent = relation == null ? "<missing>" : relation.GetSource().Word();
mentions.Add(m_2.mentionNum.ToString(), Javax.Json.Json.CreateObjectBuilder().Add("doc_id", id).Add("mention_id", m_2.mentionID).Add("mention_num", m_2.mentionNum).Add("sent_num", m_2.sentNum).Add("start_index", m_2.startIndex).Add("end_index"
, m_2.endIndex).Add("head_index", m_2.headIndex).Add("mention_type", m_2.mentionType.ToString()).Add("dep_relation", depRelation).Add("dep_parent", depParent).Add("sentence", GetSentenceArray(m_2.sentenceWords)).Add("contained-in-other-mention"
, mentionsByHeadIndex[m_2.headIndex].Stream().AnyMatch(null) ? 1 : 0).Build());
}
IJsonArrayBuilder featureNames = Javax.Json.Json.CreateArrayBuilder().Add("same-speaker").Add("antecedent-is-mention-speaker").Add("mention-is-antecedent-speaker").Add("relaxed-head-match").Add("exact-string-match").Add("relaxed-string-match"
);
IJsonObjectBuilder features = Javax.Json.Json.CreateObjectBuilder();
IJsonObjectBuilder labels = Javax.Json.Json.CreateObjectBuilder();
foreach (KeyValuePair <Pair <int, int>, bool> e in mentionPairs)
{
Mention m1 = document.predictedMentionsByID[e.Key.first];
Mention m2 = document.predictedMentionsByID[e.Key.second];
string key = m1.mentionNum + " " + m2.mentionNum;
IJsonArrayBuilder builder = Javax.Json.Json.CreateArrayBuilder();
foreach (int val in CategoricalFeatureExtractor.PairwiseFeatures(document, m1, m2, dictionaries, conll))
{
builder.Add(val);
}
features.Add(key, builder.Build());
labels.Add(key, e.Value ? 1 : 0);
}
IJsonObject docData = Javax.Json.Json.CreateObjectBuilder().Add("sentences", sentences.Build()).Add("mentions", mentions.Build()).Add("labels", labels.Build()).Add("pair_feature_names", featureNames.Build()).Add("pair_features", features.Build
()).Add("document_features", docFeatures.Build()).Build();
dataWriter.Println(docData);
}
