public static DepPattern PatternToDepPattern(Pair <IndexedWord, GrammaticalRelation> p, DataInstance sent)
{
Token token = new Token(PatternFactory.PatternType.Dep);
CoreLabel backingLabel = sent.GetTokens()[p.First().Index() - 1];
System.Diagnostics.Debug.Assert(backingLabel.ContainsKey(typeof(PatternsAnnotations.ProcessedTextAnnotation)), "the keyset are " + backingLabel.ToString(CoreLabel.OutputFormat.All));
token.AddORRestriction(typeof(PatternsAnnotations.ProcessedTextAnnotation), backingLabel.Get(typeof(PatternsAnnotations.ProcessedTextAnnotation)));
return(new DepPattern(token, p.Second()));
}
internal static Triple <bool, Token, string> GetContextTokenStr(CoreLabel tokenj)
{
Token strgeneric = new Token(PatternFactory.PatternType.Surface);
string strOriginal = string.Empty;
bool isLabeledO = true;
// for (Entry<String, Class<? extends TypesafeMap.Key<String>>> e : getAnswerClass().entrySet()) {
// if (!tokenj.get(e.getValue()).equals(backgroundSymbol)) {
// isLabeledO = false;
// if (strOriginal.isEmpty()) {
// strOriginal = e.getKey();
// } else {
// strOriginal += "|" + e.getKey();
// }
// strgeneric.addRestriction(e.getKey(), e.getKey());
// }
// }
foreach (KeyValuePair <string, Type> e in ConstantsAndVariables.GetGeneralizeClasses())
{
if (!tokenj.ContainsKey(e.Value) || tokenj.Get(e.Value) == null)
{
throw new Exception(" Why does the token not have the class " + e.Value + " set? Existing classes " + tokenj.ToString(CoreLabel.OutputFormat.All));
}
if (!tokenj.Get(e.Value).Equals(ConstantsAndVariables.backgroundSymbol))
{
isLabeledO = false;
if (strOriginal.IsEmpty())
{
strOriginal = e.Key;
}
else
{
strOriginal += "|" + e.Key;
}
strgeneric.AddORRestriction(e.Value, e.Key);
}
}
if (useContextNERRestriction)
{
string nerTag = tokenj.Get(typeof(CoreAnnotations.NamedEntityTagAnnotation));
if (nerTag != null && !nerTag.Equals(SeqClassifierFlags.DefaultBackgroundSymbol))
{
isLabeledO = false;
if (strOriginal.IsEmpty())
{
strOriginal = nerTag;
}
else
{
strOriginal += "|" + nerTag;
}
strgeneric.AddORRestriction(typeof(CoreAnnotations.NamedEntityTagAnnotation), nerTag);
}
}
return(new Triple <bool, Token, string>(isLabeledO, strgeneric, strOriginal));
}
/// <summary>
/// Create a new search problem instance, given a sentence (possibly fragment), and the corresponding
/// parse tree.
/// </summary>
/// <param name="parseTree">The original tree of the sentence we are beginning with</param>
/// <param name="truthOfPremise">The truth of the premise. In most applications, this will just be true.</param>
/// <returns>A new search problem instance.</returns>
public virtual ForwardEntailerSearchProblem Apply(SemanticGraph parseTree, bool truthOfPremise)
{
foreach (IndexedWord vertex in parseTree.VertexSet())
{
CoreLabel token = vertex.BackingLabel();
if (token != null && !token.ContainsKey(typeof(NaturalLogicAnnotations.PolarityAnnotation)))
{
throw new ArgumentException("Cannot run Natural Logic forward entailment without polarity annotations set. See " + typeof(NaturalLogicAnnotator).GetSimpleName());
}
}
return(new ForwardEntailerSearchProblem(parseTree, truthOfPremise, maxResults, maxTicks, weights));
}
/// <summary>Create a datum from a string.</summary>
/// <remarks>
/// Create a datum from a string. The CoreAnnotations must correspond to those used by
/// SequenceClassifier. The following annotations are copied from the provided
/// CoreLabel cl, if present:
/// DomainAnnotation
/// startOffset and endOffset will be added to the
/// <see cref="Edu.Stanford.Nlp.Ling.CoreAnnotations.CharacterOffsetBeginAnnotation"/>
/// of
/// the
/// <see cref="Edu.Stanford.Nlp.Ling.CoreLabel"/>
/// cl to give the
/// <see cref="Edu.Stanford.Nlp.Ling.CoreAnnotations.CharacterOffsetBeginAnnotation"/>
/// and
/// <see cref="Edu.Stanford.Nlp.Ling.CoreAnnotations.CharacterOffsetEndAnnotation"/>
/// of the resulting datum.
/// </remarks>
private static CoreLabel CreateDatum(CoreLabel cl, string token, string label, int startOffset, int endOffset)
{
CoreLabel newTok = new CoreLabel();
newTok.Set(typeof(CoreAnnotations.TextAnnotation), token);
newTok.Set(typeof(CoreAnnotations.CharAnnotation), token);
newTok.Set(typeof(CoreAnnotations.AnswerAnnotation), label);
newTok.Set(typeof(CoreAnnotations.GoldAnswerAnnotation), label);
newTok.Set(typeof(CoreAnnotations.CharacterOffsetBeginAnnotation), cl.Get(typeof(CoreAnnotations.CharacterOffsetBeginAnnotation)) + startOffset);
newTok.Set(typeof(CoreAnnotations.CharacterOffsetEndAnnotation), cl.Get(typeof(CoreAnnotations.CharacterOffsetBeginAnnotation)) + endOffset);
if (cl != null && cl.ContainsKey(typeof(CoreAnnotations.DomainAnnotation)))
{
newTok.Set(typeof(CoreAnnotations.DomainAnnotation), cl.Get(typeof(CoreAnnotations.DomainAnnotation)));
}
return(newTok);
}
protected internal override T GetNext()
{
try
{
T nextToken;
do
{
// initialized in do-while
// Depending on the orthographic normalization options,
// some tokens can be obliterated. In this case, keep iterating
// until we see a non-zero length token.
nextToken = (splitAny && !compoundBuffer.IsEmpty()) ? (T)compoundBuffer.Remove(0) : (T)lexer.Next();
}while (nextToken != null && nextToken.Word().IsEmpty());
// Check for compounds to split
if (splitAny && nextToken is CoreLabel)
{
CoreLabel cl = (CoreLabel)nextToken;
if (cl.ContainsKey(typeof(CoreAnnotations.ParentAnnotation)))
{
if (splitCompounds && cl.Get(typeof(CoreAnnotations.ParentAnnotation)).Equals(SpanishLexer.CompoundAnnotation))
{
nextToken = (T)ProcessCompound(cl);
}
else
{
if (splitVerbs && cl.Get(typeof(CoreAnnotations.ParentAnnotation)).Equals(SpanishLexer.VbPronAnnotation))
{
nextToken = (T)ProcessVerb(cl);
}
else
{
if (splitContractions && cl.Get(typeof(CoreAnnotations.ParentAnnotation)).Equals(SpanishLexer.ContrAnnotation))
{
nextToken = (T)ProcessContraction(cl);
}
}
}
}
}
return(nextToken);
}
catch (IOException e)
{
throw new RuntimeIOException(e);
}
}
private static Tree FindTreeWithSpan(Tree tree, int start, int end)
{
CoreLabel l = (CoreLabel)tree.Label();
if (l != null && l.ContainsKey(typeof(CoreAnnotations.BeginIndexAnnotation)) && l.ContainsKey(typeof(CoreAnnotations.EndIndexAnnotation)))
{
int myStart = l.Get(typeof(CoreAnnotations.BeginIndexAnnotation));
int myEnd = l.Get(typeof(CoreAnnotations.EndIndexAnnotation));
if (start == myStart && end == myEnd)
{
// found perfect match
return(tree);
}
else
{
if (end < myStart)
{
return(null);
}
else
{
if (start >= myEnd)
{
return(null);
}
}
}
}
// otherwise, check inside children - a match is possible
foreach (Tree kid in tree.Children())
{
if (kid == null)
{
continue;
}
Tree ret = FindTreeWithSpan(kid, start, end);
// found matching child
if (ret != null)
{
return(ret);
}
}
// no match
return(null);
}
protected internal override T GetNext()
{
try
{
T nextToken = null;
do
{
// Depending on the orthographic normalization options,
// some tokens can be obliterated. In this case, keep iterating
// until we see a non-zero length token.
nextToken = ((splitContractions || splitCompounds) && compoundBuffer.Count > 0) ? (T)compoundBuffer.Remove(0) : (T)lexer.Next();
}while (nextToken != null && nextToken.Word().Length == 0);
// Check for compounds to split
if (splitCompounds && nextToken is CoreLabel)
{
CoreLabel cl = (CoreLabel)nextToken;
if (cl.ContainsKey(typeof(CoreAnnotations.ParentAnnotation)) && cl.Get(typeof(CoreAnnotations.ParentAnnotation)).Equals(FrenchLexer.CompoundAnnotation))
{
nextToken = (T)ProcessCompound(cl);
}
}
// Check for contractions to split
if (splitContractions && nextToken is CoreLabel)
{
CoreLabel cl = (CoreLabel)nextToken;
if (cl.ContainsKey(typeof(CoreAnnotations.ParentAnnotation)) && cl.Get(typeof(CoreAnnotations.ParentAnnotation)).Equals(FrenchLexer.ContrAnnotation))
{
nextToken = (T)ProcessContraction(cl);
}
}
return(nextToken);
}
catch (IOException e)
{
throw new RuntimeIOException(e);
}
}
/// <exception cref="System.Exception"/>
public virtual Triple <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> >, ICollection <CandidatePhrase> > Call()
{
// CollectionValuedMap<String, Integer> tokensMatchedPattern = new
// CollectionValuedMap<String, Integer>();
try
{
ICollection <CandidatePhrase> alreadyLabeledPhrases = new HashSet <CandidatePhrase>();
TwoDimensionalCounter <CandidatePhrase, E> allFreq = new TwoDimensionalCounter <CandidatePhrase, E>();
CollectionValuedMap <E, Triple <string, int, int> > matchedTokensByPat = new CollectionValuedMap <E, Triple <string, int, int> >();
foreach (string sentid in sentids)
{
IList <CoreLabel> sent = sents[sentid].GetTokens();
foreach (KeyValuePair <TokenSequencePattern, E> pEn in patterns)
{
if (pEn.Key == null)
{
throw new Exception("why is the pattern " + pEn + " null?");
}
TokenSequenceMatcher m = ((TokenSequenceMatcher)pEn.Key.GetMatcher(sent));
// //Setting this find type can save time in searching - greedy and reluctant quantifiers are not enforced
// m.setFindType(SequenceMatcher.FindType.FIND_ALL);
//Higher branch values makes the faster but uses more memory
m.SetBranchLimit(5);
while (m.Find())
{
int s = m.Start("$term");
int e = m.End("$term");
System.Diagnostics.Debug.Assert(e - s <= PatternFactory.numWordsCompoundMapped[label], "How come the pattern " + pEn.Key + " is extracting phrases longer than numWordsCompound of " + PatternFactory.numWordsCompoundMapped[label] + " for label "
+ label);
string phrase = string.Empty;
string phraseLemma = string.Empty;
bool useWordNotLabeled = false;
bool doNotUse = false;
//find if the neighboring words are labeled - if so - club them together
if (constVars.clubNeighboringLabeledWords)
{
for (int i = s - 1; i >= 0; i--)
{
if (!sent[i].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
s = i + 1;
break;
}
}
for (int i_1 = e; i_1 < sent.Count; i_1++)
{
if (!sent[i_1].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
e = i_1;
break;
}
}
}
//to make sure we discard phrases with stopwords in between, but include the ones in which stop words were removed at the ends if removeStopWordsFromSelectedPhrases is true
bool[] addedindices = new bool[e - s];
// Arrays.fill(addedindices, false); // not needed as initialized false
for (int i_2 = s; i_2 < e; i_2++)
{
CoreLabel l = sent[i_2];
l.Set(typeof(PatternsAnnotations.MatchedPattern), true);
if (!l.ContainsKey(typeof(PatternsAnnotations.MatchedPatterns)) || l.Get(typeof(PatternsAnnotations.MatchedPatterns)) == null)
{
l.Set(typeof(PatternsAnnotations.MatchedPatterns), new HashSet <Pattern>());
}
SurfacePattern pSur = (SurfacePattern)pEn.Value;
System.Diagnostics.Debug.Assert(pSur != null, "Why is " + pEn.Value + " not present in the index?!");
System.Diagnostics.Debug.Assert(l.Get(typeof(PatternsAnnotations.MatchedPatterns)) != null, "How come MatchedPatterns class is null for the token. The classes in the key set are " + l.KeySet());
l.Get(typeof(PatternsAnnotations.MatchedPatterns)).Add(pSur);
foreach (KeyValuePair <Type, object> ig in constVars.GetIgnoreWordswithClassesDuringSelection()[label])
{
if (l.ContainsKey(ig.Key) && l.Get(ig.Key).Equals(ig.Value))
{
doNotUse = true;
}
}
bool containsStop = ContainsStopWord(l, constVars.GetCommonEngWords(), PatternFactory.ignoreWordRegex);
if (removePhrasesWithStopWords && containsStop)
{
doNotUse = true;
}
else
{
if (!containsStop || !removeStopWordsFromSelectedPhrases)
{
if (label == null || l.Get(constVars.GetAnswerClass()[label]) == null || !l.Get(constVars.GetAnswerClass()[label]).Equals(label))
{
useWordNotLabeled = true;
}
phrase += " " + l.Word();
phraseLemma += " " + l.Lemma();
addedindices[i_2 - s] = true;
}
}
}
for (int i_3 = 0; i_3 < addedindices.Length; i_3++)
{
if (i_3 > 0 && i_3 < addedindices.Length - 1 && addedindices[i_3 - 1] == true && addedindices[i_3] == false && addedindices[i_3 + 1] == true)
{
doNotUse = true;
break;
}
}
if (!doNotUse)
{
matchedTokensByPat.Add(pEn.Value, new Triple <string, int, int>(sentid, s, e - 1));
phrase = phrase.Trim();
if (!phrase.IsEmpty())
{
phraseLemma = phraseLemma.Trim();
CandidatePhrase candPhrase = CandidatePhrase.CreateOrGet(phrase, phraseLemma);
allFreq.IncrementCount(candPhrase, pEn.Value, 1.0);
if (!useWordNotLabeled)
{
alreadyLabeledPhrases.Add(candPhrase);
}
}
}
}
}
}
return(new Triple <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> >, ICollection <CandidatePhrase> >(allFreq, matchedTokensByPat, alreadyLabeledPhrases));
}
catch (Exception e)
{
logger.Error(e);
throw;
}
}
/// <exception cref="System.Exception"/>
public virtual Pair <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> > > Call()
{
// CollectionValuedMap<String, Integer> tokensMatchedPattern = new
// CollectionValuedMap<String, Integer>();
TwoDimensionalCounter <CandidatePhrase, E> allFreq = new TwoDimensionalCounter <CandidatePhrase, E>();
CollectionValuedMap <E, Triple <string, int, int> > matchedTokensByPat = new CollectionValuedMap <E, Triple <string, int, int> >();
foreach (string sentid in sentids)
{
DataInstance sent = sents[sentid];
IList <CoreLabel> tokens = sent.GetTokens();
foreach (KeyValuePair <SemgrexPattern, E> pEn in patterns)
{
if (pEn.Key == null)
{
throw new Exception("why is the pattern " + pEn + " null?");
}
SemanticGraph graph = ((DataInstanceDep)sent).GetGraph();
//SemgrexMatcher m = pEn.getKey().matcher(graph);
//TokenSequenceMatcher m = pEn.getKey().matcher(sent);
// //Setting this find type can save time in searching - greedy and reluctant quantifiers are not enforced
// m.setFindType(SequenceMatcher.FindType.FIND_ALL);
//Higher branch values makes the faster but uses more memory
//m.setBranchLimit(5);
ICollection <ExtractedPhrase> matched = GetMatchedTokensIndex(graph, pEn.Key, sent, label);
foreach (ExtractedPhrase match in matched)
{
int s = match.startIndex;
int e = match.endIndex + 1;
string phrase = string.Empty;
string phraseLemma = string.Empty;
bool useWordNotLabeled = false;
bool doNotUse = false;
//find if the neighboring words are labeled - if so - club them together
if (constVars.clubNeighboringLabeledWords)
{
for (int i = s - 1; i >= 0; i--)
{
if (tokens[i].Get(constVars.GetAnswerClass()[label]).Equals(label) && (e - i + 1) <= PatternFactory.numWordsCompoundMapped[label])
{
s = i;
}
else
{
//System.out.println("for phrase " + match + " clubbing earlier word. new s is " + s);
break;
}
}
for (int i_1 = e; i_1 < tokens.Count; i_1++)
{
if (tokens[i_1].Get(constVars.GetAnswerClass()[label]).Equals(label) && (i_1 - s + 1) <= PatternFactory.numWordsCompoundMapped[label])
{
e = i_1;
}
else
{
//System.out.println("for phrase " + match + " clubbing next word. new e is " + e);
break;
}
}
}
//to make sure we discard phrases with stopwords in between, but include the ones in which stop words were removed at the ends if removeStopWordsFromSelectedPhrases is true
bool[] addedindices = new bool[e - s];
// Arrays.fill(addedindices, false); // get for free on array initialization
for (int i_2 = s; i_2 < e; i_2++)
{
CoreLabel l = tokens[i_2];
l.Set(typeof(PatternsAnnotations.MatchedPattern), true);
if (!l.ContainsKey(typeof(PatternsAnnotations.MatchedPatterns)) || l.Get(typeof(PatternsAnnotations.MatchedPatterns)) == null)
{
l.Set(typeof(PatternsAnnotations.MatchedPatterns), new HashSet <Pattern>());
}
Pattern pSur = pEn.Value;
System.Diagnostics.Debug.Assert(pSur != null, "Why is " + pEn.Value + " not present in the index?!");
System.Diagnostics.Debug.Assert(l.Get(typeof(PatternsAnnotations.MatchedPatterns)) != null, "How come MatchedPatterns class is null for the token. The classes in the key set are " + l.KeySet());
l.Get(typeof(PatternsAnnotations.MatchedPatterns)).Add(pSur);
foreach (KeyValuePair <Type, object> ig in constVars.GetIgnoreWordswithClassesDuringSelection()[label])
{
if (l.ContainsKey(ig.Key) && l.Get(ig.Key).Equals(ig.Value))
{
doNotUse = true;
}
}
bool containsStop = ContainsStopWord(l, constVars.GetCommonEngWords(), PatternFactory.ignoreWordRegex);
if (removePhrasesWithStopWords && containsStop)
{
doNotUse = true;
}
else
{
if (!containsStop || !removeStopWordsFromSelectedPhrases)
{
if (label == null || l.Get(constVars.GetAnswerClass()[label]) == null || !l.Get(constVars.GetAnswerClass()[label]).Equals(label))
{
useWordNotLabeled = true;
}
phrase += " " + l.Word();
phraseLemma += " " + l.Lemma();
addedindices[i_2 - s] = true;
}
}
}
for (int i_3 = 0; i_3 < addedindices.Length; i_3++)
{
if (i_3 > 0 && i_3 < addedindices.Length - 1 && addedindices[i_3 - 1] == true && addedindices[i_3] == false && addedindices[i_3 + 1] == true)
{
doNotUse = true;
break;
}
}
if (!doNotUse && useWordNotLabeled)
{
matchedTokensByPat.Add(pEn.Value, new Triple <string, int, int>(sentid, s, e - 1));
if (useWordNotLabeled)
{
phrase = phrase.Trim();
phraseLemma = phraseLemma.Trim();
allFreq.IncrementCount(CandidatePhrase.CreateOrGet(phrase, phraseLemma, match.GetFeatures()), pEn.Value, 1.0);
}
}
}
}
}
return(new Pair <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> > >(allFreq, matchedTokensByPat));
}
/// <summary>Take a dataset Annotation, generate their parse trees and identify syntactic heads (and head spans, if necessary)</summary>
public virtual void PreProcessSentences(Annotation dataset)
{
logger.Severe("GenericDataSetReader: Started pre-processing the corpus...");
// run the processor, i.e., NER, parse etc.
if (processor != null)
{
// we might already have syntactic annotation from offline files
IList <ICoreMap> sentences = dataset.Get(typeof(CoreAnnotations.SentencesAnnotation));
if (sentences.Count > 0 && !sentences[0].ContainsKey(typeof(TreeCoreAnnotations.TreeAnnotation)))
{
logger.Info("Annotating dataset with " + processor);
processor.Annotate(dataset);
}
else
{
logger.Info("Found existing syntactic annotations. Will not use the NLP processor.");
}
}
/*
* List<CoreMap> sentences = dataset.get(CoreAnnotations.SentencesAnnotation.class);
* for(int i = 0; i < sentences.size(); i ++){
* CoreMap sent = sentences.get(i);
* List<CoreLabel> tokens = sent.get(CoreAnnotations.TokensAnnotation.class);
* logger.info("Tokens for sentence #" + i + ": " + tokens);
* logger.info("Parse tree for sentence #" + i + ": " + sent.get(TreeCoreAnnotations.TreeAnnotation.class).pennString());
* }
*/
IList <ICoreMap> sentences_1 = dataset.Get(typeof(CoreAnnotations.SentencesAnnotation));
logger.Fine("Extracted " + sentences_1.Count + " sentences.");
foreach (ICoreMap sentence in sentences_1)
{
IList <CoreLabel> tokens = sentence.Get(typeof(CoreAnnotations.TokensAnnotation));
logger.Fine("Processing sentence " + tokens);
Tree tree = sentence.Get(typeof(TreeCoreAnnotations.TreeAnnotation));
if (tree == null)
{
throw new Exception("ERROR: MR requires full syntactic analysis!");
}
// convert tree labels to CoreLabel if necessary
// we need this because we store additional info in the CoreLabel, such as the spans of each tree
ConvertToCoreLabels(tree);
// store the tree spans, if not present already
CoreLabel l = (CoreLabel)tree.Label();
if (forceGenerationOfIndexSpans || (!l.ContainsKey(typeof(CoreAnnotations.BeginIndexAnnotation)) && !l.ContainsKey(typeof(CoreAnnotations.EndIndexAnnotation))))
{
tree.IndexSpans(0);
logger.Fine("Index spans were generated.");
}
else
{
logger.Fine("Index spans were NOT generated.");
}
logger.Fine("Parse tree using CoreLabel:\n" + tree.PennString());
//
// now match all entity mentions against the syntactic tree
//
if (sentence.Get(typeof(MachineReadingAnnotations.EntityMentionsAnnotation)) != null)
{
foreach (EntityMention ent in sentence.Get(typeof(MachineReadingAnnotations.EntityMentionsAnnotation)))
{
logger.Fine("Finding head for entity: " + ent);
int headPos = AssignSyntacticHead(ent, tree, tokens, calculateHeadSpan);
logger.Fine("Syntactic head of mention \"" + ent + "\" is: " + tokens[headPos].Word());
System.Diagnostics.Debug.Assert((ent.GetExtent() != null));
System.Diagnostics.Debug.Assert((ent.GetHead() != null));
System.Diagnostics.Debug.Assert((ent.GetSyntacticHeadTokenPosition() >= 0));
}
}
}
logger.Severe("GenericDataSetReader: Pre-processing complete.");
}
/// <exception cref="System.Exception"/>
public virtual Pair <TwoDimensionalCounter <Pair <string, string>, E>, CollectionValuedMap <E, Triple <string, int, int> > > Call()
{
//CollectionValuedMap<String, Integer> tokensMatchedPattern = new CollectionValuedMap<String, Integer>();
CollectionValuedMap <E, Triple <string, int, int> > matchedTokensByPat = new CollectionValuedMap <E, Triple <string, int, int> >();
TwoDimensionalCounter <Pair <string, string>, E> allFreq = new TwoDimensionalCounter <Pair <string, string>, E>();
foreach (string sentid in sentids)
{
IList <CoreLabel> sent = sents[sentid].GetTokens();
//FIND_ALL is faster than FIND_NONOVERLAP
IEnumerable <ISequenceMatchResult <ICoreMap> > matched = multiPatternMatcher.Find(sent, SequenceMatcher.FindType.FindAll);
foreach (ISequenceMatchResult <ICoreMap> m in matched)
{
int s = m.Start("$term");
int e = m.End("$term");
E matchedPat = patterns[m.Pattern()];
matchedTokensByPat.Add(matchedPat, new Triple <string, int, int>(sentid, s, e));
string phrase = string.Empty;
string phraseLemma = string.Empty;
bool useWordNotLabeled = false;
bool doNotUse = false;
//find if the neighboring words are labeled - if so - club them together
if (constVars.clubNeighboringLabeledWords)
{
for (int i = s - 1; i >= 0; i--)
{
if (!sent[i].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
s = i + 1;
break;
}
}
for (int i_1 = e; i_1 < sent.Count; i_1++)
{
if (!sent[i_1].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
e = i_1;
break;
}
}
}
//to make sure we discard phrases with stopwords in between, but include the ones in which stop words were removed at the ends if removeStopWordsFromSelectedPhrases is true
bool[] addedindices = new bool[e - s];
// Arrays.fill(addedindices, false); // unneeded as done on initialization
for (int i_2 = s; i_2 < e; i_2++)
{
CoreLabel l = sent[i_2];
l.Set(typeof(PatternsAnnotations.MatchedPattern), true);
if (!l.ContainsKey(typeof(PatternsAnnotations.MatchedPatterns)))
{
l.Set(typeof(PatternsAnnotations.MatchedPatterns), new HashSet <Pattern>());
}
l.Get(typeof(PatternsAnnotations.MatchedPatterns)).Add(matchedPat);
// if (restrictToMatched) {
// tokensMatchedPattern.add(sentid, i);
// }
foreach (KeyValuePair <Type, object> ig in constVars.GetIgnoreWordswithClassesDuringSelection()[label])
{
if (l.ContainsKey(ig.Key) && l.Get(ig.Key).Equals(ig.Value))
{
doNotUse = true;
}
}
bool containsStop = ContainsStopWord(l, constVars.GetCommonEngWords(), PatternFactory.ignoreWordRegex);
if (removePhrasesWithStopWords && containsStop)
{
doNotUse = true;
}
else
{
if (!containsStop || !removeStopWordsFromSelectedPhrases)
{
if (label == null || l.Get(constVars.GetAnswerClass()[label]) == null || !l.Get(constVars.GetAnswerClass()[label]).Equals(label.ToString()))
{
useWordNotLabeled = true;
}
phrase += " " + l.Word();
phraseLemma += " " + l.Lemma();
addedindices[i_2 - s] = true;
}
}
}
for (int i_3 = 0; i_3 < addedindices.Length; i_3++)
{
if (i_3 > 0 && i_3 < addedindices.Length - 1 && addedindices[i_3 - 1] == true && addedindices[i_3] == false && addedindices[i_3 + 1] == true)
{
doNotUse = true;
break;
}
}
if (!doNotUse && useWordNotLabeled)
{
phrase = phrase.Trim();
phraseLemma = phraseLemma.Trim();
allFreq.IncrementCount(new Pair <string, string>(phrase, phraseLemma), matchedPat, 1.0);
}
}
}
// for (SurfacePattern pat : patterns.keySet()) {
// String patternStr = pat.toString();
//
// TokenSequencePattern p = TokenSequencePattern.compile(constVars.env.get(label), patternStr);
// if (pat == null || p == null)
// throw new RuntimeException("why is the pattern " + pat + " null?");
//
// TokenSequenceMatcher m = p.getMatcher(sent);
// while (m.find()) {
//
// int s = m.start("$term");
// int e = m.end("$term");
//
// String phrase = "";
// String phraseLemma = "";
// boolean useWordNotLabeled = false;
// boolean doNotUse = false;
// for (int i = s; i < e; i++) {
// CoreLabel l = sent.get(i);
// l.set(PatternsAnnotations.MatchedPattern.class, true);
// if (restrictToMatched) {
// tokensMatchedPattern.add(sentid, i);
// }
// for (Entry<Class, Object> ig : constVars.ignoreWordswithClassesDuringSelection.get(label).entrySet()) {
// if (l.containsKey(ig.getKey()) && l.get(ig.getKey()).equals(ig.getValue())) {
// doNotUse = true;
// }
// }
// boolean containsStop = containsStopWord(l, constVars.getCommonEngWords(), constVars.ignoreWordRegex, ignoreWords);
// if (removePhrasesWithStopWords && containsStop) {
// doNotUse = true;
// } else {
// if (!containsStop || !removeStopWordsFromSelectedPhrases) {
//
// if (label == null || l.get(constVars.answerClass.get(label)) == null || !l.get(constVars.answerClass.get(label)).equals(label.toString())) {
// useWordNotLabeled = true;
// }
// phrase += " " + l.word();
// phraseLemma += " " + l.lemma();
//
// }
// }
// }
// if (!doNotUse && useWordNotLabeled) {
// phrase = phrase.trim();
// phraseLemma = phraseLemma.trim();
// allFreq.incrementCount(new Pair<String, String>(phrase, phraseLemma), pat, 1.0);
// }
// }
// }
return(new Pair <TwoDimensionalCounter <Pair <string, string>, E>, CollectionValuedMap <E, Triple <string, int, int> > >(allFreq, matchedTokensByPat));
}
