public override bool CheckEntityMatch(Document document, CorefCluster mentionCluster, CorefCluster potentialAntecedent, Dictionaries dict, ICollection <Mention> roleSet)
{
bool matched = false;
Mention mainMention = mentionCluster.GetRepresentativeMention();
Mention antMention = potentialAntecedent.GetRepresentativeMention();
// Check if the representative mentions are compatible
if (IsNamedMention(mainMention, dict, roleSet) && IsNamedMention(antMention, dict, roleSet))
{
if (mainMention.originalSpan.Count > minTokens || antMention.originalSpan.Count > minTokens)
{
if (CorefRules.EntityAttributesAgree(mentionCluster, potentialAntecedent, ignoreGender))
{
if (supportedNerTypes.Contains(mainMention.nerString) || supportedNerTypes.Contains(antMention.nerString))
{
matched = mentionMatcher.IsCompatible(mainMention, antMention);
if (matched != null)
{
//Redwood.log("Match '" + mainMention + "' with '" + antMention + "' => " + matched);
if (!matched)
{
document.AddIncompatible(mainMention, antMention);
}
}
else
{
matched = false;
}
}
}
}
}
return(matched);
}
/// <summary>Skip this mention? (search pruning)</summary>
public virtual bool SkipThisMention(Document document, Mention m1, CorefCluster c, Dictionaries dict)
{
bool skip = false;
// only do for the first mention in its cluster
// if(!flags.USE_EXACTSTRINGMATCH && !flags.USE_ROLEAPPOSITION && !flags.USE_PREDICATENOMINATIVES
if (!flags.UseRoleapposition && !flags.UsePredicatenominatives && !flags.UseAcronym && !flags.UseApposition && !flags.UseRelativepronoun && !c.GetFirstMention().Equals(m1))
{
// CHINESE CHANGE
return(true);
}
if (m1.appositions == null && m1.predicateNominatives == null && (m1.LowercaseNormalizedSpanString().StartsWith("a ") || m1.LowercaseNormalizedSpanString().StartsWith("an ")) && !flags.UseExactstringmatch)
{
skip = true;
}
// A noun phrase starting with an indefinite article - unlikely to have an antecedent (e.g. "A commission" was set up to .... )
if (dict.indefinitePronouns.Contains(m1.LowercaseNormalizedSpanString()))
{
skip = true;
}
// An indefinite pronoun - unlikely to have an antecedent (e.g. "Some" say that... )
foreach (string indef in dict.indefinitePronouns)
{
if (m1.LowercaseNormalizedSpanString().StartsWith(indef + " "))
{
skip = true;
// A noun phrase starting with an indefinite adjective - unlikely to have an antecedent (e.g. "Another opinion" on the topic is...)
break;
}
}
return(skip);
}
/// <summary>Skip this mention? (search pruning)</summary>
public virtual bool SkipThisMention(Document document, Mention m1, CorefCluster c, Dictionaries dict)
{
bool skip = false;
// only do for the first mention in its cluster
if (!flags.UseExactstringmatch && !flags.UseRoleapposition && !flags.UsePredicatenominatives && !flags.UseAcronym && !flags.UseApposition && !flags.UseRelativepronoun && !c.GetFirstMention().Equals(m1))
{
return(true);
}
SieveCoreferenceSystem.logger.Finest("DOING COREF FOR:\t" + m1.SpanToString());
if (m1.appositions == null && m1.predicateNominatives == null && (m1.LowercaseNormalizedSpanString().StartsWith("a ") || m1.LowercaseNormalizedSpanString().StartsWith("an ")) && !flags.UseExactstringmatch)
{
skip = true;
}
// A noun phrase starting with an indefinite article - unlikely to have an antecedent (e.g. "A commission" was set up to .... )
if (dict.indefinitePronouns.Contains(m1.LowercaseNormalizedSpanString()))
{
skip = true;
}
// An indefinite pronoun - unlikely to have an antecedent (e.g. "Some" say that... )
foreach (string indef in dict.indefinitePronouns)
{
if (m1.LowercaseNormalizedSpanString().StartsWith(indef + " "))
{
skip = true;
// A noun phrase starting with an indefinite adjective - unlikely to have an antecedent (e.g. "Another opinion" on the topic is...)
break;
}
}
if (skip)
{
SieveCoreferenceSystem.logger.Finest("MENTION SKIPPED:\t" + m1.SpanToString() + "(" + m1.sentNum + ")" + "\toriginalRef: " + m1.originalRef + " in discourse " + m1.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)));
}
return(skip);
}
public static void Merge(Document document, int mID, int antID)
{
CorefCluster c1 = document.corefClusters[document.predictedMentionsByID[mID].corefClusterID];
CorefCluster c2 = document.corefClusters[document.predictedMentionsByID[antID].corefClusterID];
if (c1 == c2)
{
return;
}
int removeID = c1.GetClusterID();
CorefCluster.MergeClusters(c2, c1);
document.MergeIncompatibles(c2, c1);
Sharpen.Collections.Remove(document.corefClusters, removeID);
}
public static void MergeCoreferenceClusters(Pair <int, int> mentionPair, Document document)
{
Mention m1 = document.predictedMentionsByID[mentionPair.first];
Mention m2 = document.predictedMentionsByID[mentionPair.second];
if (m1.corefClusterID == m2.corefClusterID)
{
return;
}
int removeId = m1.corefClusterID;
CorefCluster c1 = document.corefClusters[m1.corefClusterID];
CorefCluster c2 = document.corefClusters[m2.corefClusterID];
CorefCluster.MergeClusters(c2, c1);
Sharpen.Collections.Remove(document.corefClusters, removeId);
}
private ICounter <string> GetFeatures(Document doc, Mention m1, Mention m2)
{
System.Diagnostics.Debug.Assert((m1.AppearEarlierThan(m2)));
ICounter <string> features = new ClassicCounter <string>();
// global features
features.IncrementCount("bias");
if (useDocSource)
{
features.IncrementCount("doc-type=" + doc.docType);
if (doc.docInfo != null && doc.docInfo.Contains("DOC_ID"))
{
features.IncrementCount("doc-source=" + doc.docInfo["DOC_ID"].Split("/")[1]);
}
}
// singleton feature conjunctions
IList <string> singletonFeatures1 = m1.GetSingletonFeatures(dictionaries);
IList <string> singletonFeatures2 = m2.GetSingletonFeatures(dictionaries);
foreach (KeyValuePair <int, string> e in SingletonFeatures)
{
if (e.Key < singletonFeatures1.Count && e.Key < singletonFeatures2.Count)
{
features.IncrementCount(e.Value + "=" + singletonFeatures1[e.Key] + "_" + singletonFeatures2[e.Key]);
}
}
SemanticGraphEdge p1 = GetDependencyParent(m1);
SemanticGraphEdge p2 = GetDependencyParent(m2);
features.IncrementCount("dep-relations=" + (p1 == null ? "null" : p1.GetRelation()) + "_" + (p2 == null ? "null" : p2.GetRelation()));
features.IncrementCount("roles=" + GetRole(m1) + "_" + GetRole(m2));
CoreLabel headCL1 = HeadWord(m1);
CoreLabel headCL2 = HeadWord(m2);
string headPOS1 = GetPOS(headCL1);
string headPOS2 = GetPOS(headCL2);
features.IncrementCount("head-pos-s=" + headPOS1 + "_" + headPOS2);
features.IncrementCount("head-words=" + WordIndicator("h_" + headCL1.Word().ToLower() + "_" + headCL2.Word().ToLower(), headPOS1 + "_" + headPOS2));
// agreement features
AddFeature(features, "animacies-agree", m2.AnimaciesAgree(m1));
AddFeature(features, "attributes-agree", m2.AttributesAgree(m1, dictionaries));
AddFeature(features, "entity-types-agree", m2.EntityTypesAgree(m1, dictionaries));
AddFeature(features, "numbers-agree", m2.NumbersAgree(m1));
AddFeature(features, "genders-agree", m2.GendersAgree(m1));
AddFeature(features, "ner-strings-equal", m1.nerString.Equals(m2.nerString));
// string matching features
AddFeature(features, "antecedent-head-in-anaphor", HeadContainedIn(m1, m2));
AddFeature(features, "anaphor-head-in-antecedent", HeadContainedIn(m2, m1));
if (m1.mentionType != Dictionaries.MentionType.Pronominal && m2.mentionType != Dictionaries.MentionType.Pronominal)
{
AddFeature(features, "antecedent-in-anaphor", m2.SpanToString().ToLower().Contains(m1.SpanToString().ToLower()));
AddFeature(features, "anaphor-in-antecedent", m1.SpanToString().ToLower().Contains(m2.SpanToString().ToLower()));
AddFeature(features, "heads-equal", Sharpen.Runtime.EqualsIgnoreCase(m1.headString, m2.headString));
AddFeature(features, "heads-agree", m2.HeadsAgree(m1));
AddFeature(features, "exact-match", m1.ToString().Trim().ToLower().Equals(m2.ToString().Trim().ToLower()));
AddFeature(features, "partial-match", RelaxedStringMatch(m1, m2));
double editDistance = StringUtils.EditDistance(m1.SpanToString(), m2.SpanToString()) / (double)(m1.SpanToString().Length + m2.SpanToString().Length);
features.IncrementCount("edit-distance", editDistance);
features.IncrementCount("edit-distance=" + ((int)(editDistance * 10) / 10.0));
double headEditDistance = StringUtils.EditDistance(m1.headString, m2.headString) / (double)(m1.headString.Length + m2.headString.Length);
features.IncrementCount("head-edit-distance", headEditDistance);
features.IncrementCount("head-edit-distance=" + ((int)(headEditDistance * 10) / 10.0));
}
// distance features
AddNumeric(features, "mention-distance", m2.mentionNum - m1.mentionNum);
AddNumeric(features, "sentence-distance", m2.sentNum - m1.sentNum);
if (m2.sentNum == m1.sentNum)
{
AddNumeric(features, "word-distance", m2.startIndex - m1.endIndex);
if (m1.endIndex > m2.startIndex)
{
features.IncrementCount("spans-intersect");
}
}
// setup for dcoref features
ICollection <Mention> ms1 = new HashSet <Mention>();
ms1.Add(m1);
ICollection <Mention> ms2 = new HashSet <Mention>();
ms2.Add(m2);
Random r = new Random();
CorefCluster c1 = new CorefCluster(20000 + r.NextInt(10000), ms1);
CorefCluster c2 = new CorefCluster(10000 + r.NextInt(10000), ms2);
string s2 = m2.LowercaseNormalizedSpanString();
string s1 = m1.LowercaseNormalizedSpanString();
// discourse dcoref features
AddFeature(features, "mention-speaker-PER0", Sharpen.Runtime.EqualsIgnoreCase(m2.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation)), "PER0"));
AddFeature(features, "antecedent-is-anaphor-speaker", CorefRules.AntecedentIsMentionSpeaker(doc, m2, m1, dictionaries));
AddFeature(features, "same-speaker", CorefRules.EntitySameSpeaker(doc, m2, m1));
AddFeature(features, "person-disagree-same-speaker", CorefRules.EntityPersonDisagree(doc, m2, m1, dictionaries) && CorefRules.EntitySameSpeaker(doc, m2, m1));
AddFeature(features, "antecedent-matches-anaphor-speaker", CorefRules.AntecedentMatchesMentionSpeakerAnnotation(m2, m1, doc));
AddFeature(features, "discourse-you-PER0", m2.person == Dictionaries.Person.You && doc.docType == Document.DocType.Article && m2.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation)).Equals("PER0"));
AddFeature(features, "speaker-match-i-i", m2.number == Dictionaries.Number.Singular && dictionaries.firstPersonPronouns.Contains(s1) && m1.number == Dictionaries.Number.Singular && dictionaries.firstPersonPronouns.Contains(s2) && CorefRules.
EntitySameSpeaker(doc, m2, m1));
AddFeature(features, "speaker-match-speaker-i", m2.number == Dictionaries.Number.Singular && dictionaries.firstPersonPronouns.Contains(s2) && CorefRules.AntecedentIsMentionSpeaker(doc, m2, m1, dictionaries));
AddFeature(features, "speaker-match-i-speaker", m1.number == Dictionaries.Number.Singular && dictionaries.firstPersonPronouns.Contains(s1) && CorefRules.AntecedentIsMentionSpeaker(doc, m1, m2, dictionaries));
AddFeature(features, "speaker-match-you-you", dictionaries.secondPersonPronouns.Contains(s1) && dictionaries.secondPersonPronouns.Contains(s2) && CorefRules.EntitySameSpeaker(doc, m2, m1));
AddFeature(features, "discourse-between-two-person", ((m2.person == Dictionaries.Person.I && m1.person == Dictionaries.Person.You || (m2.person == Dictionaries.Person.You && m1.person == Dictionaries.Person.I)) && (m2.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation
)) - m1.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)) == 1) && doc.docType == Document.DocType.Conversation));
AddFeature(features, "incompatible-not-match", m1.person != Dictionaries.Person.I && m2.person != Dictionaries.Person.I && (CorefRules.AntecedentIsMentionSpeaker(doc, m1, m2, dictionaries) || CorefRules.AntecedentIsMentionSpeaker(doc, m2, m1
, dictionaries)));
int utteranceDist = Math.Abs(m1.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)) - m2.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)));
if (doc.docType != Document.DocType.Article && utteranceDist == 1 && !CorefRules.EntitySameSpeaker(doc, m2, m1))
{
AddFeature(features, "speaker-mismatch-i-i", m1.person == Dictionaries.Person.I && m2.person == Dictionaries.Person.I);
AddFeature(features, "speaker-mismatch-you-you", m1.person == Dictionaries.Person.You && m2.person == Dictionaries.Person.You);
AddFeature(features, "speaker-mismatch-we-we", m1.person == Dictionaries.Person.We && m2.person == Dictionaries.Person.We);
}
// other dcoref features
string firstWord1 = FirstWord(m1).Word().ToLower();
AddFeature(features, "indefinite-article-np", (m1.appositions == null && m1.predicateNominatives == null && (firstWord1.Equals("a") || firstWord1.Equals("an"))));
AddFeature(features, "far-this", m2.LowercaseNormalizedSpanString().Equals("this") && Math.Abs(m2.sentNum - m1.sentNum) > 3);
AddFeature(features, "per0-you-in-article", m2.person == Dictionaries.Person.You && doc.docType == Document.DocType.Article && m2.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation)).Equals("PER0"));
AddFeature(features, "inside-in", m2.InsideIn(m1) || m1.InsideIn(m2));
AddFeature(features, "indefinite-determiners", dictionaries.indefinitePronouns.Contains(m1.originalSpan[0].Lemma()) || dictionaries.indefinitePronouns.Contains(m2.originalSpan[0].Lemma()));
AddFeature(features, "entity-attributes-agree", CorefRules.EntityAttributesAgree(c2, c1));
AddFeature(features, "entity-token-distance", CorefRules.EntityTokenDistance(m2, m1));
AddFeature(features, "i-within-i", CorefRules.EntityIWithinI(m2, m1, dictionaries));
AddFeature(features, "exact-string-match", CorefRules.EntityExactStringMatch(c2, c1, dictionaries, doc.roleSet));
AddFeature(features, "entity-relaxed-heads-agree", CorefRules.EntityRelaxedHeadsAgreeBetweenMentions(c2, c1, m2, m1));
AddFeature(features, "is-acronym", CorefRules.EntityIsAcronym(doc, c2, c1));
AddFeature(features, "demonym", m2.IsDemonym(m1, dictionaries));
AddFeature(features, "incompatible-modifier", CorefRules.EntityHaveIncompatibleModifier(m2, m1));
AddFeature(features, "head-lemma-match", m1.headWord.Lemma().Equals(m2.headWord.Lemma()));
AddFeature(features, "words-included", CorefRules.EntityWordsIncluded(c2, c1, m2, m1));
AddFeature(features, "extra-proper-noun", CorefRules.EntityHaveExtraProperNoun(m2, m1, new HashSet <string>()));
AddFeature(features, "number-in-later-mentions", CorefRules.EntityNumberInLaterMention(m2, m1));
AddFeature(features, "sentence-context-incompatible", CorefRules.SentenceContextIncompatible(m2, m1, dictionaries));
// syntax features
if (useConstituencyParse)
{
if (m1.sentNum == m2.sentNum)
{
int clauseCount = 0;
Tree tree = m2.contextParseTree;
Tree current = m2.mentionSubTree;
while (true)
{
current = current.Ancestor(1, tree);
if (current.Label().Value().StartsWith("S"))
{
clauseCount++;
}
if (current.Dominates(m1.mentionSubTree))
{
break;
}
if (current.Label().Value().Equals("ROOT") || current.Ancestor(1, tree) == null)
{
break;
}
}
features.IncrementCount("clause-count", clauseCount);
features.IncrementCount("clause-count=" + Bin(clauseCount));
}
if (RuleBasedCorefMentionFinder.IsPleonastic(m2, m2.contextParseTree) || RuleBasedCorefMentionFinder.IsPleonastic(m1, m1.contextParseTree))
{
features.IncrementCount("pleonastic-it");
}
if (MaximalNp(m1.mentionSubTree) == MaximalNp(m2.mentionSubTree))
{
features.IncrementCount("same-maximal-np");
}
bool m1Embedded = HeadEmbeddingLevel(m1.mentionSubTree, m1.headIndex - m1.startIndex) > 1;
bool m2Embedded = HeadEmbeddingLevel(m2.mentionSubTree, m2.headIndex - m2.startIndex) > 1;
features.IncrementCount("embedding=" + m1Embedded + "_" + m2Embedded);
}
return(features);
}
/// <exception cref="System.Exception"/>
public override void FindCoreferentAntecedent(Mention m, int mIdx, Document document, Dictionaries dict, Properties props, StringBuilder sbLog)
{
// check for skip: first mention only, discourse salience
if (!this.flags.UseSpeakermatch && !this.flags.UseDiscoursematch && !this.flags.UseApposition && !this.flags.UsePredicatenominatives && this.SkipThisMention(document, m, document.corefClusters[m.corefClusterID], dict))
{
return;
}
ICollection <Mention> roleSet = document.roleSet;
for (int sentJ = m.sentNum; sentJ >= 0; sentJ--)
{
IList <Mention> l = Edu.Stanford.Nlp.Coref.Hybrid.Sieve.Sieve.GetOrderedAntecedents(m, sentJ, mIdx, document.predictedMentions, dict);
if (maxSentDist != -1 && m.sentNum - sentJ > maxSentDist)
{
continue;
}
// TODO: do we need this?
// Sort mentions by length whenever we have two mentions beginning at the same position and having the same head
for (int i = 0; i < l.Count; i++)
{
for (int j = 0; j < l.Count; j++)
{
if (l[i].headString.Equals(l[j].headString) && l[i].startIndex == l[j].startIndex && l[i].SameSentence(l[j]) && j > i && l[i].SpanToString().Length > l[j].SpanToString().Length)
{
l.Set(j, l.Set(i, l[j]));
}
}
}
// log.info("antecedent ordering changed!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!");
foreach (Mention ant in l)
{
if (SkipForAnalysis(ant, m, props))
{
continue;
}
// m2 - antecedent of m1
// Skip singletons according to the singleton predictor
// (only for non-NE mentions)
// Recasens, de Marneffe, and Potts (NAACL 2013)
if (m.isSingleton && m.mentionType != Dictionaries.MentionType.Proper && ant.isSingleton && ant.mentionType != Dictionaries.MentionType.Proper)
{
continue;
}
if (m.corefClusterID == ant.corefClusterID)
{
continue;
}
if (!mType.Contains(m.mentionType) || !aType.Contains(ant.mentionType))
{
continue;
}
if (m.mentionType == Dictionaries.MentionType.Pronominal)
{
if (!MatchedMentionType(m, mTypeStr))
{
continue;
}
if (!MatchedMentionType(ant, aTypeStr))
{
continue;
}
}
CorefCluster c1 = document.corefClusters[m.corefClusterID];
CorefCluster c2 = document.corefClusters[ant.corefClusterID];
System.Diagnostics.Debug.Assert((c1 != null));
System.Diagnostics.Debug.Assert((c2 != null));
if (this.UseRoleSkip())
{
if (m.IsRoleAppositive(ant, dict))
{
roleSet.Add(m);
}
else
{
if (ant.IsRoleAppositive(m, dict))
{
roleSet.Add(ant);
}
}
continue;
}
if (this.Coreferent(document, c1, c2, m, ant, dict, roleSet))
{
// print logs for analysis
// if (doScore()) {
// printLogs(c1, c2, m1, m2, document, currentSieve);
// }
// print dcoref log
if (HybridCorefProperties.Debug(props))
{
sbLog.Append(HybridCorefPrinter.PrintErrorLogDcoref(m, ant, document, dict, mIdx, this.GetType().FullName));
}
int removeID = c1.clusterID;
// log.info("Merging ant "+c2+" with "+c1);
CorefCluster.MergeClusters(c2, c1);
document.MergeIncompatibles(c2, c1);
document.MergeAcronymCache(c2, c1);
// log.warning("Removing cluster " + removeID + ", merged with " + c2.getClusterID());
Sharpen.Collections.Remove(document.corefClusters, removeID);
return;
}
}
}
}
/// <summary>Checks if two clusters are coreferent according to our sieve pass constraints</summary>
/// <param name="document"/>
/// <exception cref="System.Exception"/>
public virtual bool Coreferent(Document document, CorefCluster mentionCluster, CorefCluster potentialAntecedent, Mention mention2, Mention ant, Dictionaries dict, ICollection <Mention> roleSet)
{
bool ret = false;
Mention mention = mentionCluster.GetRepresentativeMention();
if (flags.UseIncompatibles)
{
// Check our list of incompatible mentions and don't cluster them together
// Allows definite no's from previous sieves to propagate down
if (document.IsIncompatible(mentionCluster, potentialAntecedent))
{
return(false);
}
}
if (flags.DoPronoun && Math.Abs(mention2.sentNum - ant.sentNum) > 3 && mention2.person != Dictionaries.Person.I && mention2.person != Dictionaries.Person.You)
{
return(false);
}
if (mention2.LowercaseNormalizedSpanString().Equals("this") && Math.Abs(mention2.sentNum - ant.sentNum) > 3)
{
return(false);
}
if (mention2.person == Dictionaries.Person.You && document.docType == Document.DocType.Article && mention2.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation)).Equals("PER0"))
{
return(false);
}
if (document.conllDoc != null)
{
if (ant.generic && ant.person == Dictionaries.Person.You)
{
return(false);
}
if (mention2.generic)
{
return(false);
}
}
// chinese newswire contains coref nested NPs with shared headword Chen & Ng
if (lang != Locale.Chinese || document.docInfo == null || !document.docInfo.GetOrDefault("DOC_ID", string.Empty).Contains("nw"))
{
if (mention2.InsideIn(ant) || ant.InsideIn(mention2))
{
return(false);
}
}
if (flags.UseSpeakermatch)
{
string mSpeaker = mention2.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation));
string aSpeaker = ant.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation));
// <I> from same speaker
if (mention2.person == Dictionaries.Person.I && ant.person == Dictionaries.Person.I)
{
return(mSpeaker.Equals(aSpeaker));
}
// <I> - speaker
if ((mention2.person == Dictionaries.Person.I && mSpeaker.Equals(int.ToString(ant.mentionID))) || (ant.person == Dictionaries.Person.I && aSpeaker.Equals(int.ToString(mention2.mentionID))))
{
return(true);
}
}
if (flags.UseDiscoursematch)
{
string mString = mention.LowercaseNormalizedSpanString();
string antString = ant.LowercaseNormalizedSpanString();
// mention and ant both belong to the same speaker cluster
if (mention.speakerInfo != null && mention.speakerInfo == ant.speakerInfo)
{
return(true);
}
// (I - I) in the same speaker's quotation.
if (mention.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(mString) && ant.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(antString) && CorefRules.EntitySameSpeaker(document, mention,
ant))
{
return(true);
}
// (speaker - I)
if ((mention.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(mString)) && CorefRules.AntecedentIsMentionSpeaker(document, mention, ant, dict))
{
if (mention.speakerInfo == null && ant.speakerInfo != null)
{
mention.speakerInfo = ant.speakerInfo;
}
return(true);
}
// (I - speaker)
if ((ant.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(antString)) && CorefRules.AntecedentIsMentionSpeaker(document, ant, mention, dict))
{
if (ant.speakerInfo == null && mention.speakerInfo != null)
{
ant.speakerInfo = mention.speakerInfo;
}
return(true);
}
// Can be iffy if more than two speakers... but still should be okay most of the time
if (dict.secondPersonPronouns.Contains(mString) && dict.secondPersonPronouns.Contains(antString) && CorefRules.EntitySameSpeaker(document, mention, ant))
{
return(true);
}
// previous I - you or previous you - I in two person conversation
if (((mention.person == Dictionaries.Person.I && ant.person == Dictionaries.Person.You || (mention.person == Dictionaries.Person.You && ant.person == Dictionaries.Person.I)) && (mention.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation
)) - ant.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)) == 1) && document.docType == Document.DocType.Conversation))
{
return(true);
}
if (dict.reflexivePronouns.Contains(mention.headString) && CorefRules.EntitySubjectObject(mention, ant))
{
return(true);
}
}
if (!flags.UseExactstringmatch && !flags.UseRelaxedExactstringmatch && !flags.UseApposition && !flags.UseWordsInclusion)
{
foreach (Mention m in mentionCluster.GetCorefMentions())
{
foreach (Mention a in potentialAntecedent.GetCorefMentions())
{
// angelx - not sure about the logic here, disable (code was also refactored from original)
// vv gabor - re-enabled code (seems to improve performance) vv
if (m.person != Dictionaries.Person.I && a.person != Dictionaries.Person.I && (CorefRules.AntecedentIsMentionSpeaker(document, m, a, dict) || CorefRules.AntecedentIsMentionSpeaker(document, a, m, dict)))
{
document.AddIncompatible(m, a);
return(false);
}
// ^^ end block of code in question ^^
int dist = Math.Abs(m.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)) - a.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)));
if (document.docType != Document.DocType.Article && dist == 1 && !CorefRules.EntitySameSpeaker(document, m, a))
{
string mSpeaker = document.speakers[m.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation))];
string aSpeaker = document.speakers[a.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation))];
if (m.person == Dictionaries.Person.I && a.person == Dictionaries.Person.I)
{
document.AddIncompatible(m, a);
return(false);
}
if (m.person == Dictionaries.Person.You && a.person == Dictionaries.Person.You)
{
document.AddIncompatible(m, a);
return(false);
}
// This is weak since we can refer to both speakers
if (m.person == Dictionaries.Person.We && a.person == Dictionaries.Person.We)
{
document.AddIncompatible(m, a);
return(false);
}
}
}
}
if (document.docType == Document.DocType.Article)
{
foreach (Mention m_1 in mentionCluster.GetCorefMentions())
{
foreach (Mention a in potentialAntecedent.GetCorefMentions())
{
if (CorefRules.EntitySubjectObject(m_1, a))
{
document.AddIncompatible(m_1, a);
return(false);
}
}
}
}
}
// Incompatibility constraints - do before match checks
if (flags.USE_iwithini && CorefRules.EntityIWithinI(mention, ant, dict))
{
document.AddIncompatible(mention, ant);
return(false);
}
// Match checks
if (flags.UseExactstringmatch && CorefRules.EntityExactStringMatch(mention, ant, dict, roleSet))
{
return(true);
}
// if(flags.USE_EXACTSTRINGMATCH && Rules.entityExactStringMatch(mentionCluster, potentialAntecedent, dict, roleSet)){
// return true;
// }
if (flags.UseNameMatch && CheckEntityMatch(document, mentionCluster, potentialAntecedent, dict, roleSet))
{
ret = true;
}
if (flags.UseRelaxedExactstringmatch && CorefRules.EntityRelaxedExactStringMatch(mentionCluster, potentialAntecedent, mention, ant, dict, roleSet))
{
return(true);
}
if (flags.UseApposition && CorefRules.EntityIsApposition(mentionCluster, potentialAntecedent, mention, ant))
{
return(true);
}
if (flags.UsePredicatenominatives && CorefRules.EntityIsPredicateNominatives(mentionCluster, potentialAntecedent, mention, ant))
{
return(true);
}
if (flags.UseAcronym && CorefRules.EntityIsAcronym(document, mentionCluster, potentialAntecedent))
{
return(true);
}
if (flags.UseRelativepronoun && CorefRules.EntityIsRelativePronoun(mention, ant))
{
return(true);
}
if (flags.UseDemonym && mention.IsDemonym(ant, dict))
{
return(true);
}
if (flags.UseRoleapposition)
{
if (lang == Locale.Chinese)
{
ret = false;
}
else
{
if (CorefRules.EntityIsRoleAppositive(mentionCluster, potentialAntecedent, mention, ant, dict))
{
ret = true;
}
}
}
if (flags.UseInclusionHeadmatch && CorefRules.EntityHeadsAgree(mentionCluster, potentialAntecedent, mention, ant, dict))
{
ret = true;
}
if (flags.UseRelaxedHeadmatch && CorefRules.EntityRelaxedHeadsAgreeBetweenMentions(mentionCluster, potentialAntecedent, mention, ant))
{
ret = true;
}
if (flags.UseWordsInclusion && ret && !CorefRules.EntityWordsIncluded(mentionCluster, potentialAntecedent, mention, ant))
{
return(false);
}
if (flags.UseIncompatibleModifier && ret && CorefRules.EntityHaveIncompatibleModifier(mentionCluster, potentialAntecedent))
{
return(false);
}
if (flags.UseProperheadAtLast && ret && !CorefRules.EntitySameProperHeadLastWord(mentionCluster, potentialAntecedent, mention, ant))
{
return(false);
}
if (flags.UseAttributesAgree && !CorefRules.EntityAttributesAgree(mentionCluster, potentialAntecedent))
{
return(false);
}
if (flags.UseDifferentLocation && CorefRules.EntityHaveDifferentLocation(mention, ant, dict))
{
if (flags.UseProperheadAtLast && ret && mention.goldCorefClusterID != ant.goldCorefClusterID)
{
}
return(false);
}
if (flags.UseNumberInMention && CorefRules.EntityNumberInLaterMention(mention, ant))
{
if (flags.UseProperheadAtLast && ret && mention.goldCorefClusterID != ant.goldCorefClusterID)
{
}
return(false);
}
if (flags.UseDistance && CorefRules.EntityTokenDistance(mention2, ant))
{
return(false);
}
if (flags.UseCorefDict)
{
// Head match
if (ant.headWord.Lemma().Equals(mention2.headWord.Lemma()))
{
return(false);
}
// Constraint: ignore pairs commonNoun - properNoun
if (ant.mentionType != Dictionaries.MentionType.Proper && (mention2.headWord.Get(typeof(CoreAnnotations.PartOfSpeechAnnotation)).StartsWith("NNP") || !Sharpen.Runtime.Substring(mention2.headWord.Word(), 1).Equals(Sharpen.Runtime.Substring(mention2
.headWord.Word(), 1).ToLower())))
{
return(false);
}
// Constraint: ignore plurals
if (ant.headWord.Get(typeof(CoreAnnotations.PartOfSpeechAnnotation)).Equals("NNS") && mention2.headWord.Get(typeof(CoreAnnotations.PartOfSpeechAnnotation)).Equals("NNS"))
{
return(false);
}
// Constraint: ignore mentions with indefinite determiners
if (dict.indefinitePronouns.Contains(ant.originalSpan[0].Lemma()) || dict.indefinitePronouns.Contains(mention2.originalSpan[0].Lemma()))
{
return(false);
}
// Constraint: ignore coordinated mentions
if (ant.IsCoordinated() || mention2.IsCoordinated())
{
return(false);
}
// Constraint: context incompatibility
if (CorefRules.ContextIncompatible(mention2, ant, dict))
{
return(false);
}
// Constraint: sentence context incompatibility when the mentions are common nouns
if (CorefRules.SentenceContextIncompatible(mention2, ant, dict))
{
return(false);
}
if (CorefRules.EntityClusterAllCorefDictionary(mentionCluster, potentialAntecedent, dict, 1, 8))
{
return(true);
}
if (CorefRules.EntityCorefDictionary(mention, ant, dict, 2, 2))
{
return(true);
}
if (CorefRules.EntityCorefDictionary(mention, ant, dict, 3, 2))
{
return(true);
}
if (CorefRules.EntityCorefDictionary(mention, ant, dict, 4, 2))
{
return(true);
}
}
if (flags.DoPronoun)
{
Mention m;
if (mention.predicateNominatives != null && mention.predicateNominatives.Contains(mention2))
{
m = mention2;
}
else
{
m = mention;
}
bool mIsPronoun = (m.IsPronominal() || dict.allPronouns.Contains(m.ToString()));
bool attrAgree = HybridCorefProperties.UseDefaultPronounAgreement(props) ? CorefRules.EntityAttributesAgree(mentionCluster, potentialAntecedent) : CorefRules.EntityAttributesAgree(mentionCluster, potentialAntecedent, lang);
if (mIsPronoun && attrAgree)
{
if (dict.demonymSet.Contains(ant.LowercaseNormalizedSpanString()) && dict.notOrganizationPRP.Contains(m.headString))
{
document.AddIncompatible(m, ant);
return(false);
}
if (CorefRules.EntityPersonDisagree(document, mentionCluster, potentialAntecedent, dict))
{
document.AddIncompatible(m, ant);
return(false);
}
return(true);
}
}
if (flags.UseChineseHeadMatch)
{
if (mention2.headWord == ant.headWord && mention2.InsideIn(ant))
{
if (!document.IsCoref(mention2, ant))
{
}
// TODO: exclude conjunction
// log.info("error in chinese head match: "+mention2.spanToString()+"\t"+ant.spanToString());
return(true);
}
}
return(ret);
}
public virtual bool CheckEntityMatch(Document document, CorefCluster mentionCluster, CorefCluster potentialAntecedent, Dictionaries dict, ICollection <Mention> roleSet)
{
return(false);
}
/// <summary>Checks if two clusters are coreferent according to our sieve pass constraints.</summary>
/// <param name="document"/>
/// <exception cref="System.Exception"/>
public virtual bool Coreferent(Document document, CorefCluster mentionCluster, CorefCluster potentialAntecedent, Mention mention2, Mention ant, Dictionaries dict, ICollection <Mention> roleSet, Semantics semantics)
{
bool ret = false;
Mention mention = mentionCluster.GetRepresentativeMention();
if (flags.UseIncompatibles)
{
// Check our list of incompatible mentions and don't cluster them together
// Allows definite no's from previous sieves to propagate down
if (document.IsIncompatible(mentionCluster, potentialAntecedent))
{
SieveCoreferenceSystem.logger.Finest("INCOMPATIBLE clusters: not match: " + ant.SpanToString() + "(" + ant.mentionID + ") :: " + mention.SpanToString() + "(" + mention.mentionID + ") -> " + (mention.goldCorefClusterID != ant.goldCorefClusterID
));
return(false);
}
}
if (flags.DoPronoun && Math.Abs(mention2.sentNum - ant.sentNum) > 3 && mention2.person != Dictionaries.Person.I && mention2.person != Dictionaries.Person.You)
{
return(false);
}
if (mention2.LowercaseNormalizedSpanString().Equals("this") && Math.Abs(mention2.sentNum - ant.sentNum) > 3)
{
return(false);
}
if (mention2.person == Dictionaries.Person.You && document.docType == Document.DocType.Article && mention2.headWord.Get(typeof(CoreAnnotations.SpeakerAnnotation)).Equals("PER0"))
{
return(false);
}
if (document.conllDoc != null)
{
if (ant.generic && ant.person == Dictionaries.Person.You)
{
return(false);
}
if (mention2.generic)
{
return(false);
}
}
if (mention2.InsideIn(ant) || ant.InsideIn(mention2))
{
return(false);
}
if (flags.UseDiscoursematch)
{
string mString = mention.LowercaseNormalizedSpanString();
string antString = ant.LowercaseNormalizedSpanString();
// mention and ant both belong to the same speaker cluster
if (mention.speakerInfo != null && mention.speakerInfo == ant.speakerInfo)
{
SieveCoreferenceSystem.logger.Finest("discourse match: maps to same speaker: " + mention.SpanToString() + "\tmatched\t" + ant.SpanToString());
return(true);
}
// (I - I) in the same speaker's quotation.
if (mention.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(mString) && ant.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(antString) && Rules.EntitySameSpeaker(document, mention, ant))
{
SieveCoreferenceSystem.logger.Finest("discourse match: 1st person same speaker: " + mention.SpanToString() + "\tmatched\t" + ant.SpanToString());
return(true);
}
// (speaker - I)
if ((mention.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(mString)) && Rules.AntecedentIsMentionSpeaker(document, mention, ant, dict))
{
SieveCoreferenceSystem.logger.Finest("discourse match: 1st person mention speaker match antecedent: " + mention.SpanToString() + "\tmatched\t" + ant.SpanToString());
if (mention.speakerInfo == null && ant.speakerInfo != null)
{
mention.speakerInfo = ant.speakerInfo;
}
return(true);
}
// (I - speaker)
if ((ant.number == Dictionaries.Number.Singular && dict.firstPersonPronouns.Contains(antString)) && Rules.AntecedentIsMentionSpeaker(document, ant, mention, dict))
{
SieveCoreferenceSystem.logger.Finest("discourse match: 1st person antecedent speaker match mention: " + mention.SpanToString() + "\tmatched\t" + ant.SpanToString());
if (ant.speakerInfo == null && mention.speakerInfo != null)
{
ant.speakerInfo = mention.speakerInfo;
}
return(true);
}
// Can be iffy if more than two speakers... but still should be okay most of the time
if (dict.secondPersonPronouns.Contains(mString) && dict.secondPersonPronouns.Contains(antString) && Rules.EntitySameSpeaker(document, mention, ant))
{
SieveCoreferenceSystem.logger.Finest("discourse match: 2nd person same speaker: " + mention.SpanToString() + "\tmatched\t" + ant.SpanToString());
return(true);
}
// previous I - you or previous you - I in two person conversation
if (((mention.person == Dictionaries.Person.I && ant.person == Dictionaries.Person.You || (mention.person == Dictionaries.Person.You && ant.person == Dictionaries.Person.I)) && (mention.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation
)) - ant.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)) == 1) && document.docType == Document.DocType.Conversation))
{
SieveCoreferenceSystem.logger.Finest("discourse match: between two person: " + mention.SpanToString() + "\tmatched\t" + ant.SpanToString());
return(true);
}
if (dict.reflexivePronouns.Contains(mention.headString) && Rules.EntitySubjectObject(mention, ant))
{
SieveCoreferenceSystem.logger.Finest("discourse match: reflexive pronoun: " + ant.SpanToString() + "(" + ant.mentionID + ") :: " + mention.SpanToString() + "(" + mention.mentionID + ") -> " + (mention.goldCorefClusterID == ant.goldCorefClusterID
));
return(true);
}
}
if (Constants.UseDiscourseConstraints && !flags.UseExactstringmatch && !flags.UseRelaxedExactstringmatch && !flags.UseApposition && !flags.UseWordsInclusion)
{
foreach (Mention m in mentionCluster.GetCorefMentions())
{
foreach (Mention a in potentialAntecedent.GetCorefMentions())
{
// angelx - not sure about the logic here, disable (code was also refactored from original)
// vv gabor - re-enabled code (seems to improve performance) vv
if (m.person != Dictionaries.Person.I && a.person != Dictionaries.Person.I && (Rules.AntecedentIsMentionSpeaker(document, m, a, dict) || Rules.AntecedentIsMentionSpeaker(document, a, m, dict)))
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: not match(speaker): " + ant.SpanToString() + "(" + ant.mentionID + ") :: " + mention.SpanToString() + "(" + mention.mentionID + ") -> " + (mention.goldCorefClusterID != ant.goldCorefClusterID
));
document.AddIncompatible(m, a);
return(false);
}
// ^^ end block of code in question ^^
int dist = Math.Abs(m.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)) - a.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation)));
if (document.docType != Document.DocType.Article && dist == 1 && !Rules.EntitySameSpeaker(document, m, a))
{
string mSpeaker = document.speakers[m.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation))];
string aSpeaker = document.speakers[a.headWord.Get(typeof(CoreAnnotations.UtteranceAnnotation))];
if (m.person == Dictionaries.Person.I && a.person == Dictionaries.Person.I)
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: neighbor I: " + ant.SpanToString() + "(" + ant.mentionID + "," + aSpeaker + ") :: " + mention.SpanToString() + "(" + mention.mentionID + "," + mSpeaker + ") -> " + (mention.goldCorefClusterID
!= ant.goldCorefClusterID));
document.AddIncompatible(m, a);
return(false);
}
if (m.person == Dictionaries.Person.You && a.person == Dictionaries.Person.You)
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: neighbor YOU: " + ant.SpanToString() + "(" + ant.mentionID + "," + aSpeaker + ") :: " + mention.SpanToString() + "(" + mention.mentionID + "," + mSpeaker + ") -> " + (mention.goldCorefClusterID
!= ant.goldCorefClusterID));
document.AddIncompatible(m, a);
return(false);
}
// This is weak since we can refer to both speakers
if (m.person == Dictionaries.Person.We && a.person == Dictionaries.Person.We)
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: neighbor WE: " + ant.SpanToString() + "(" + ant.mentionID + "," + aSpeaker + ") :: " + mention.SpanToString() + "(" + mention.mentionID + "," + mSpeaker + ") -> " + (mention.goldCorefClusterID
!= ant.goldCorefClusterID));
document.AddIncompatible(m, a);
return(false);
}
}
}
}
if (document.docType == Document.DocType.Article)
{
foreach (Mention m_1 in mentionCluster.GetCorefMentions())
{
foreach (Mention a in potentialAntecedent.GetCorefMentions())
{
if (Rules.EntitySubjectObject(m_1, a))
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: subject-object: " + ant.SpanToString() + "(" + ant.mentionID + ") :: " + mention.SpanToString() + "(" + mention.mentionID + ") -> " + (mention.goldCorefClusterID != ant.goldCorefClusterID)
);
document.AddIncompatible(m_1, a);
return(false);
}
}
}
}
}
// Incompatibility constraints - do before match checks
if (flags.USE_iwithini && Rules.EntityIWithinI(mention, ant, dict))
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: iwithini: " + ant.SpanToString() + "(" + ant.mentionID + ") :: " + mention.SpanToString() + "(" + mention.mentionID + ") -> " + (mention.goldCorefClusterID != ant.goldCorefClusterID));
document.AddIncompatible(mention, ant);
return(false);
}
// Match checks
if (flags.UseExactstringmatch && Rules.EntityExactStringMatch(mentionCluster, potentialAntecedent, dict, roleSet))
{
return(true);
}
if (flags.UseNameMatch && CheckEntityMatch(document, mentionCluster, potentialAntecedent, dict, roleSet))
{
ret = true;
}
if (flags.UseRelaxedExactstringmatch && Rules.EntityRelaxedExactStringMatch(mentionCluster, potentialAntecedent, mention, ant, dict, roleSet))
{
return(true);
}
if (flags.UseApposition && Rules.EntityIsApposition(mentionCluster, potentialAntecedent, mention, ant))
{
SieveCoreferenceSystem.logger.Finest("Apposition: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
return(true);
}
if (flags.UsePredicatenominatives && Rules.EntityIsPredicateNominatives(mentionCluster, potentialAntecedent, mention, ant))
{
SieveCoreferenceSystem.logger.Finest("Predicate nominatives: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
return(true);
}
if (flags.UseAcronym && Rules.EntityIsAcronym(document, mentionCluster, potentialAntecedent))
{
SieveCoreferenceSystem.logger.Finest("Acronym: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
return(true);
}
if (flags.UseRelativepronoun && Rules.EntityIsRelativePronoun(mention, ant))
{
SieveCoreferenceSystem.logger.Finest("Relative pronoun: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
return(true);
}
if (flags.UseDemonym && mention.IsDemonym(ant, dict))
{
SieveCoreferenceSystem.logger.Finest("Demonym: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
return(true);
}
if (flags.UseRoleapposition && lang != Locale.Chinese && Rules.EntityIsRoleAppositive(mentionCluster, potentialAntecedent, mention, ant, dict))
{
SieveCoreferenceSystem.logger.Finest("Role Appositive: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
ret = true;
}
if (flags.UseInclusionHeadmatch && Rules.EntityHeadsAgree(mentionCluster, potentialAntecedent, mention, ant, dict))
{
SieveCoreferenceSystem.logger.Finest("Entity heads agree: " + mention.SpanToString() + "\tvs\t" + ant.SpanToString());
ret = true;
}
if (flags.UseRelaxedHeadmatch && Rules.EntityRelaxedHeadsAgreeBetweenMentions(mentionCluster, potentialAntecedent, mention, ant))
{
ret = true;
}
if (flags.UseWordsInclusion && ret && !Rules.EntityWordsIncluded(mentionCluster, potentialAntecedent, mention, ant))
{
return(false);
}
if (flags.UseIncompatibleModifier && ret && Rules.EntityHaveIncompatibleModifier(mentionCluster, potentialAntecedent))
{
return(false);
}
if (flags.UseProperheadAtLast && ret && !Rules.EntitySameProperHeadLastWord(mentionCluster, potentialAntecedent, mention, ant))
{
return(false);
}
if (flags.UseAttributesAgree && !Rules.EntityAttributesAgree(mentionCluster, potentialAntecedent))
{
return(false);
}
if (flags.UseDifferentLocation && Rules.EntityHaveDifferentLocation(mention, ant, dict))
{
if (flags.UseProperheadAtLast && ret && mention.goldCorefClusterID != ant.goldCorefClusterID)
{
SieveCoreferenceSystem.logger.Finest("DIFFERENT LOCATION: " + ant.SpanToString() + " :: " + mention.SpanToString());
}
return(false);
}
if (flags.UseNumberInMention && Rules.EntityNumberInLaterMention(mention, ant))
{
if (flags.UseProperheadAtLast && ret && mention.goldCorefClusterID != ant.goldCorefClusterID)
{
SieveCoreferenceSystem.logger.Finest("NEW NUMBER : " + ant.SpanToString() + " :: " + mention.SpanToString());
}
return(false);
}
if (flags.UseWnHypernym)
{
MethodInfo meth = semantics.wordnet.GetType().GetMethod("checkHypernym", typeof(CorefCluster), typeof(CorefCluster), typeof(Mention), typeof(Mention));
if ((bool)meth.Invoke(semantics.wordnet, mentionCluster, potentialAntecedent, mention, ant))
{
ret = true;
}
else
{
if (mention.goldCorefClusterID == ant.goldCorefClusterID && !mention.IsPronominal() && !ant.IsPronominal())
{
SieveCoreferenceSystem.logger.Finest("not hypernym in WN");
SieveCoreferenceSystem.logger.Finest("False Negatives:: " + ant.SpanToString() + " <= " + mention.SpanToString());
}
}
}
if (flags.UseWnSynonym)
{
MethodInfo meth = semantics.wordnet.GetType().GetMethod("checkSynonym", new Type[] { typeof(Mention), typeof(Mention) });
if ((bool)meth.Invoke(semantics.wordnet, mention, ant))
{
ret = true;
}
else
{
if (mention.goldCorefClusterID == ant.goldCorefClusterID && !mention.IsPronominal() && !ant.IsPronominal())
{
SieveCoreferenceSystem.logger.Finest("not synonym in WN");
SieveCoreferenceSystem.logger.Finest("False Negatives:: " + ant.SpanToString() + " <= " + mention.SpanToString());
}
}
}
try
{
if (flags.UseAlias && Rules.EntityAlias(mentionCluster, potentialAntecedent, semantics, dict))
{
return(true);
}
}
catch (Exception e)
{
throw new Exception(e);
}
if (flags.UseDistance && Rules.EntityTokenDistance(mention2, ant))
{
return(false);
}
if (flags.UseCorefDict)
{
// Head match
if (ant.headWord.Lemma().Equals(mention2.headWord.Lemma()))
{
return(false);
}
// Constraint: ignore pairs commonNoun - properNoun
if (ant.mentionType != Dictionaries.MentionType.Proper && (mention2.headWord.Get(typeof(CoreAnnotations.PartOfSpeechAnnotation)).StartsWith("NNP") || !Sharpen.Runtime.Substring(mention2.headWord.Word(), 1).Equals(Sharpen.Runtime.Substring(mention2
.headWord.Word(), 1).ToLower())))
{
return(false);
}
// Constraint: ignore plurals
if (ant.headWord.Get(typeof(CoreAnnotations.PartOfSpeechAnnotation)).Equals("NNS") && mention2.headWord.Get(typeof(CoreAnnotations.PartOfSpeechAnnotation)).Equals("NNS"))
{
return(false);
}
// Constraint: ignore mentions with indefinite determiners
if (dict.indefinitePronouns.Contains(ant.originalSpan[0].Lemma()) || dict.indefinitePronouns.Contains(mention2.originalSpan[0].Lemma()))
{
return(false);
}
// Constraint: ignore coordinated mentions
if (ant.IsCoordinated() || mention2.IsCoordinated())
{
return(false);
}
// Constraint: context incompatibility
if (Rules.ContextIncompatible(mention2, ant, dict))
{
return(false);
}
// Constraint: sentence context incompatibility when the mentions are common nouns
if (Rules.SentenceContextIncompatible(mention2, ant, dict))
{
return(false);
}
if (Rules.EntityClusterAllCorefDictionary(mentionCluster, potentialAntecedent, dict, 1, 8))
{
return(true);
}
if (Rules.EntityCorefDictionary(mention, ant, dict, 2, 2))
{
return(true);
}
if (Rules.EntityCorefDictionary(mention, ant, dict, 3, 2))
{
return(true);
}
if (Rules.EntityCorefDictionary(mention, ant, dict, 4, 2))
{
return(true);
}
}
if (flags.DoPronoun)
{
Mention m;
if (mention.predicateNominatives != null && mention.predicateNominatives.Contains(mention2))
{
m = mention2;
}
else
{
m = mention;
}
if ((m.IsPronominal() || dict.allPronouns.Contains(m.ToString())) && Rules.EntityAttributesAgree(mentionCluster, potentialAntecedent))
{
if (dict.demonymSet.Contains(ant.LowercaseNormalizedSpanString()) && dict.notOrganizationPRP.Contains(m.headString))
{
document.AddIncompatible(m, ant);
return(false);
}
if (Constants.UseDiscourseConstraints && Rules.EntityPersonDisagree(document, mentionCluster, potentialAntecedent, dict))
{
SieveCoreferenceSystem.logger.Finest("Incompatibles: Person Disagree: " + ant.SpanToString() + "(" + ant.mentionID + ") :: " + mention.SpanToString() + "(" + mention.mentionID + ") -> " + (mention.goldCorefClusterID != ant.goldCorefClusterID
));
document.AddIncompatible(m, ant);
return(false);
}
return(true);
}
}
return(ret);
}
/// <exception cref="System.Exception"/>
public static string PrintErrorLog(Mention m, Document document, ICounter <int> probs, int mIdx, Dictionaries dict, RFSieve sieve)
{
StringBuilder sb = new StringBuilder();
sb.Append("\nERROR START-----------------------------------------------------------------------\n");
sb.Append("RESOLVER TYPE: mType: " + sieve.mType + ", aType: " + sieve.aType).Append("\n");
sb.Append("DOCUMENT: " + document.docInfo["DOC_ID"] + ", " + document.docInfo["DOC_PART"]).Append("\n");
IList <Mention> orderedAnts = new List <Mention>();
sb.Append("\nGOLD CLUSTER ID\n");
for (int sentDist = m.sentNum; sentDist >= 0; sentDist--)
{
if (sentDist == sieve.maxSentDist)
{
sb.Append("\tstart compare from here-------------\n");
}
int sentIdx = m.sentNum - sentDist;
sb.Append("\tSENT " + sentIdx + "\t" + SentenceStringWithMention(sentIdx, document, true, true)).Append("\n");
}
sb.Append("\nMENTION ID\n");
for (int sentDist_1 = m.sentNum; sentDist_1 >= 0; sentDist_1--)
{
if (sentDist_1 == sieve.maxSentDist)
{
sb.Append("\tstart compare from here-------------\n");
}
int sentIdx = m.sentNum - sentDist_1;
sb.Append("\tSENT " + sentIdx + "\t" + SentenceStringWithMention(sentIdx, document, false, false)).Append("\n");
}
// get dcoref antecedents ordering
for (int sentDist_2 = 0; sentDist_2 <= Math.Min(sieve.maxSentDist, m.sentNum); sentDist_2++)
{
int sentIdx = m.sentNum - sentDist_2;
Sharpen.Collections.AddAll(orderedAnts, Edu.Stanford.Nlp.Coref.Hybrid.Sieve.Sieve.GetOrderedAntecedents(m, sentIdx, mIdx, document.predictedMentions, dict));
}
IDictionary <int, int> orders = Generics.NewHashMap();
for (int i = 0; i < orderedAnts.Count; i++)
{
Mention ant = orderedAnts[i];
orders[ant.mentionID] = i;
}
CorefCluster mC = document.corefClusters[m.corefClusterID];
bool isFirstMention = IsFirstMention(m, document);
bool foundCorefAnt = (probs.Size() > 0 && Counters.Max(probs) > sieve.thresMerge);
bool correctDecision = ((isFirstMention && !foundCorefAnt) || (foundCorefAnt && Edu.Stanford.Nlp.Coref.Hybrid.Sieve.Sieve.IsReallyCoref(document, m.mentionID, Counters.Argmax(probs))));
bool barePlural = (m.originalSpan.Count == 1 && m.headWord.Tag().Equals("NNS"));
if (correctDecision)
{
return(string.Empty);
}
sb.Append("\nMENTION: " + m.SpanToString() + " (" + m.mentionID + ")\tperson: " + m.person + "\tsingleton? " + (!m.hasTwin) + "\t\tisFirstMention? " + isFirstMention + "\t\tfoundAnt? " + foundCorefAnt + "\t\tcorrectDecision? " + correctDecision
+ "\tbarePlural? " + barePlural);
sb.Append("\n\ttype: " + m.mentionType + "\tHeadword: " + m.headWord.Word() + "\tNEtype: " + m.nerString + "\tnumber: " + m.number + "\tgender: " + m.gender + "\tanimacy: " + m.animacy).Append("\n");
if (m.contextParseTree != null)
{
sb.Append(m.contextParseTree.PennString());
}
sb.Append("\n\n\t\tOracle\t\tDcoref\t\t\tRF\t\tAntecedent\n");
foreach (int antID in Counters.ToSortedList(probs))
{
Mention ant = document.predictedMentionsByID[antID];
CorefCluster aC = document.corefClusters[ant.corefClusterID];
bool oracle = Edu.Stanford.Nlp.Coref.Hybrid.Sieve.Sieve.IsReallyCoref(document, m.mentionID, antID);
double prob = probs.GetCount(antID);
int order = orders[antID];
string oracleStr = (oracle) ? "coref " : "notcoref";
// String dcorefStr = (dcoref)? "coref " : "notcoref";
string dcorefStr = "notcoref";
if (dcorefDiscourse.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-discourse";
}
else
{
// else if(dcorefChineseHeadMatch.coreferent(document, mC, aC, m, ant, dict, null)) dcorefStr = "coref-chineseHeadMatch";
if (dcorefExactString.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-exactString";
}
else
{
if (dcorefRelaxedExactString.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-relaxedExact";
}
else
{
if (dcorefPreciseConstructs.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-preciseConstruct";
}
else
{
if (dcorefHead1.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-head1";
}
else
{
if (dcorefHead2.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-head2";
}
else
{
if (dcorefHead3.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-head3";
}
else
{
if (dcorefHead4.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-head4";
}
else
{
if (dcorefRelaxedHead.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-relaxedHead";
}
else
{
if (dcorefPronounSieve.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-pronounSieve";
}
else
{
if (dcorefSpeaker.Coreferent(document, mC, aC, m, ant, dict, null))
{
dcorefStr = "coref-speaker";
}
}
}
}
}
}
}
}
}
}
}
dcorefStr += "\t" + order.ToString();
string probStr = df.Format(prob);
sb.Append("\t\t" + oracleStr + "\t" + dcorefStr + "\t" + probStr + "\t\t" + ant.SpanToString() + " (" + ant.mentionID + ")\n");
}
sb.Append("ERROR END -----------------------------------------------------------------------\n");
return(sb.ToString());
}
/// <exception cref="System.Exception"/>
public static string PrintErrorLogDcoref(Mention m, Mention found, Document document, Dictionaries dict, int mIdx, string whichResolver)
{
StringBuilder sb = new StringBuilder();
sb.Append("\nERROR START-----------------------------------------------------------------------\n");
sb.Append("RESOLVER TYPE: ").Append(whichResolver).Append("\n");
sb.Append("DOCUMENT: " + document.docInfo["DOC_ID"] + ", " + document.docInfo["DOC_PART"]).Append("\n");
IList <Mention> orderedAnts = new List <Mention>();
sb.Append("\nGOLD CLUSTER ID\n");
for (int sentDist = m.sentNum; sentDist >= 0; sentDist--)
{
int sentIdx = m.sentNum - sentDist;
sb.Append("\tSENT " + sentIdx + "\t" + SentenceStringWithMention(sentIdx, document, true, true)).Append("\n");
}
sb.Append("\nMENTION ID\n");
for (int sentDist_1 = m.sentNum; sentDist_1 >= 0; sentDist_1--)
{
int sentIdx = m.sentNum - sentDist_1;
sb.Append("\tSENT " + sentIdx + "\t" + SentenceStringWithMention(sentIdx, document, false, false)).Append("\n");
}
// get dcoref antecedents ordering
for (int sentDist_2 = 0; sentDist_2 <= m.sentNum; sentDist_2++)
{
int sentIdx = m.sentNum - sentDist_2;
Sharpen.Collections.AddAll(orderedAnts, Edu.Stanford.Nlp.Coref.Hybrid.Sieve.Sieve.GetOrderedAntecedents(m, sentIdx, mIdx, document.predictedMentions, dict));
}
IDictionary <int, int> orders = Generics.NewHashMap();
for (int i = 0; i < orderedAnts.Count; i++)
{
Mention ant = orderedAnts[i];
orders[ant.mentionID] = i;
}
CorefCluster mC = document.corefClusters[m.corefClusterID];
bool isFirstMention = IsFirstMention(m, document);
bool foundCorefAnt = true;
// we're printing only mentions that found coref antecedent
bool correctDecision = document.IsCoref(m, found);
if (correctDecision)
{
return(string.Empty);
}
sb.Append("\nMENTION: " + m.SpanToString() + " (" + m.mentionID + ")\tperson: " + m.person + "\tsingleton? " + (!m.hasTwin) + "\t\tisFirstMention? " + isFirstMention + "\t\tfoundAnt? " + foundCorefAnt + "\t\tcorrectDecision? " + correctDecision
);
sb.Append("\n\ttype: " + m.mentionType + "\tHeadword: " + m.headWord.Word() + "\tNEtype: " + m.nerString + "\tnumber: " + m.number + "\tgender: " + m.gender + "\tanimacy: " + m.animacy).Append("\n");
if (m.contextParseTree != null)
{
sb.Append(m.contextParseTree.PennString());
}
sb.Append("\n\n\t\tOracle\t\tDcoref\t\t\tRF\t\tAntecedent\n");
foreach (Mention ant_1 in orderedAnts)
{
int antID = ant_1.mentionID;
CorefCluster aC = document.corefClusters[ant_1.corefClusterID];
bool oracle = Edu.Stanford.Nlp.Coref.Hybrid.Sieve.Sieve.IsReallyCoref(document, m.mentionID, antID);
int order = orders[antID];
string oracleStr = (oracle) ? "coref " : "notcoref";
// String dcorefStr = (dcoref)? "coref " : "notcoref";
string dcorefStr = "notcoref";
if (dcorefSpeaker.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-speaker";
}
else
{
// else if(dcorefChineseHeadMatch.coreferent(document, mC, aC, m, ant, dict, null)) dcorefStr = "coref-chineseHeadMatch";
if (dcorefDiscourse.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-discourse";
}
else
{
if (dcorefExactString.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-exactString";
}
else
{
if (dcorefRelaxedExactString.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-relaxedExact";
}
else
{
if (dcorefPreciseConstructs.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-preciseConstruct";
}
else
{
if (dcorefHead1.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-head1";
}
else
{
if (dcorefHead2.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-head2";
}
else
{
if (dcorefHead3.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-head3";
}
else
{
if (dcorefHead4.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-head4";
}
else
{
if (dcorefRelaxedHead.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-relaxedHead";
}
else
{
if (dcorefPronounSieve.Coreferent(document, mC, aC, m, ant_1, dict, null))
{
dcorefStr = "coref-pronounSieve";
}
}
}
}
}
}
}
}
}
}
}
dcorefStr += "\t" + order.ToString();
sb.Append("\t\t" + oracleStr + "\t" + dcorefStr + "\t\t" + ant_1.SpanToString() + " (" + ant_1.mentionID + ")\n");
}
sb.Append("ERROR END -----------------------------------------------------------------------\n");
return(sb.ToString());
}
