/// <summary>
/// https://universaldependencies.org/u/dep/index.html
/// Stratify a sentence according to the subject-predicate relationship
/// </summary>
/// <param name="sentence"></param>
/// <returns>sentence, subject, predicate, objective</returns>
public List <(edu.stanford.nlp.util.CoreMap, edu.stanford.nlp.ling.IndexedWord, edu.stanford.nlp.ling.IndexedWord, edu.stanford.nlp.ling.IndexedWord)> StepSamplingDependency(edu.stanford.nlp.util.CoreMap sentence)
{
List <(edu.stanford.nlp.util.CoreMap, edu.stanford.nlp.ling.IndexedWord, edu.stanford.nlp.ling.IndexedWord, edu.stanford.nlp.ling.IndexedWord)> samplings = new List <(edu.stanford.nlp.util.CoreMap, edu.stanford.nlp.ling.IndexedWord, edu.stanford.nlp.ling.IndexedWord, edu.stanford.nlp.ling.IndexedWord)>();
edu.stanford.nlp.semgraph.SemanticGraph dependencies = sentence.get(enhancedPlusPlusDependenciesAnnotationClass) as edu.stanford.nlp.semgraph.SemanticGraph;
java.util.Collection typedDependencies = dependencies.typedDependencies();
java.util.Iterator itr = typedDependencies.iterator();
while (itr.hasNext())
{
edu.stanford.nlp.trees.TypedDependency td = itr.next() as edu.stanford.nlp.trees.TypedDependency;
string relationType = td.reln().getShortName();
//Nominals
if (relationType == "nsubj" || relationType == "nsubjpass")
{
edu.stanford.nlp.ling.IndexedWord subject, predicate, objective;
subject = td.dep(); predicate = td.gov();
//在谓语位置上，缺不满足谓语角色的词，此种谓语可缺省
edu.stanford.nlp.ling.IndexedWord expl = FindIndexedWordByDependencyType(dependencies, predicate, "expl");
predicate = expl == null ? predicate : null;
//直接宾语,
objective = FindIndexedWordByDependencyType(dependencies, predicate, "obj", "dobj");
//动词或形容词的补语做宾语, open clausal complement
objective = objective ?? FindIndexedWordByDependencyType(dependencies, predicate, "ccomp", "xcomp");
//加入层次集合
samplings.Add((sentence, subject, predicate, objective));
}
}
return(samplings);
}
/// <summary>
/// 对修饰词处理
/// </summary>
private void LabelingModifiers(edu.stanford.nlp.ling.IndexedWord word, edu.stanford.nlp.util.CoreMap sentence, Scenario scenario)
{
if (word == null)
{
return;
}
List <(edu.stanford.nlp.ling.IndexedWord, string)> modifiers = word != null?FindTargetIndexWordModifier(sentence, word) : null;
string key = word.value();
string value = "";
string relation = "";
//1.根据ner，做最基本判断
foreach (var(modifier, typeName) in modifiers)
{
switch (typeName)
{
case "amod": //形容词修饰关系
{
value = modifier.value();
relation = "amod";
}
break;
case "advmod": //副词修饰关系
{
//以为 modifier 为核心搜索修饰关系， 如果存在进一步的修饰关系，则此副词为relation
relation = "advmod";
edu.stanford.nlp.ling.IndexedWord v = modifier;
}
break;
case "nummod": //额外搜寻修饰单位
{
edu.stanford.nlp.ling.IndexedWord unit = FindNumericUnit(sentence, modifier);
value = (string)modifier.get(normalizedNamedEntityTagAnnotationClass);
relation = "count";
}
break;
case "compound": //名词短语，连接key
{
key = key.InsertCompound(modifier.value());
}
break;
}
}
//1. 聚类算法，计算 relation-triple 与哪个表格匹配
IScenarioFactor pFactor = scenario.ClusterFactor(relation, key, value);
if (pFactor != null)
{
scenario.MergeValue(relation, key, value, pFactor);
}
}
/// <summary>
/// 谓语本身用途主要是是修饰主语，
/// 如果符合要求则构建 :
/// relation triple "state (s, t)"
/// </summary>
/// <param name="scenario"></param>
/// <param name="samplingSentence"></param>
/// <param name="subject"></param>
/// <param name="predicate"></param>
private void LabelingPredicate(edu.stanford.nlp.ling.IndexedWord subject, edu.stanford.nlp.ling.IndexedWord predicate, edu.stanford.nlp.ling.IndexedWord objective, edu.stanford.nlp.util.CoreMap samplingSentence, Scenario scenario)
{
string pos = predicate?.get(partOfSpeechAnnotationClass) as string;
string key = "", relation = "", value = "";
switch (pos)
{
//表示主语的状态和趋势
case "VBD":
case "VBG":
case "VBN":
case "VBP":
case "VBZ":
{
if (objective == null)
{
key = subject.value();
relation = "state";
value = predicate.value();
}
else
{
key = subject.value();
relation = predicate.value();
value = objective.value();
}
}
break;
default:
LabelingModifiers(predicate, samplingSentence, scenario);
break;
}
IScenarioFactor fa = scenario.ClusterFactor(relation, key, value);
if (fa != null)
{
scenario.MergeValue(relation, key, value, fa);
}
}
/// <summary>
/// 搜索
/// </summary>
private edu.stanford.nlp.ling.IndexedWord FindNumericUnit(edu.stanford.nlp.util.CoreMap sentence, edu.stanford.nlp.ling.IndexedWord word)
{
edu.stanford.nlp.semgraph.SemanticGraph dependencies = sentence.get(enhancedPlusPlusDependenciesAnnotationClass) as edu.stanford.nlp.semgraph.SemanticGraph;
List <edu.stanford.nlp.trees.TypedDependency> tds = FindRefs(dependencies, word.backingLabel());
foreach (edu.stanford.nlp.trees.TypedDependency td in tds)
{
}
return(null);
}
/// <summary>
///
/// </summary>
/// <param name="dependencies"></param>
/// <param name="token"></param>
/// <param name="depTypeString"></param>
/// <returns></returns>
private edu.stanford.nlp.ling.IndexedWord FindIndexedWordByDependencyType(edu.stanford.nlp.semgraph.SemanticGraph dependencies, edu.stanford.nlp.ling.IndexedWord word, params string[] depTypeString)
{
if (dependencies == null || word == null)
{
return(null);
}
List <edu.stanford.nlp.trees.TypedDependency> deps = FindRefs(dependencies, word.backingLabel());
foreach (edu.stanford.nlp.trees.TypedDependency dep in deps)
{
if (depTypeString.Contains(dep.reln().getShortName()))
{
if (dep.gov() == word)
{
return(dep.dep());
}
}
}
return(null);
}
/// <summary>
/// find the sibling relation of target word from sentence
/// </summary>
/// <param name="sentence"></param>
/// <param name="word"></param>
/// <returns>modifier words, relation type</returns>
public List <(edu.stanford.nlp.ling.IndexedWord, string)> FindTargetIndexWordModifier(edu.stanford.nlp.util.CoreMap sentence, edu.stanford.nlp.ling.IndexedWord word)
{
List <(edu.stanford.nlp.ling.IndexedWord, string)> modifiers = new List <(edu.stanford.nlp.ling.IndexedWord, string)>();
edu.stanford.nlp.semgraph.SemanticGraph dependencies = sentence.get(enhancedPlusPlusDependenciesAnnotationClass) as edu.stanford.nlp.semgraph.SemanticGraph;
List <edu.stanford.nlp.trees.TypedDependency> deps = FindRefs(dependencies, word.backingLabel());
foreach (edu.stanford.nlp.trees.TypedDependency dep in deps)
{
string relationType = dep.reln().ToString();
switch (relationType)
{
case "nummod": //数值修饰词，numeric modifier，搜索是否还存在单位修饰, 比如 200吨，10个
case "amod": //形容词修饰词，例如：红花-红
case "nmod:of": //of关系名词组，例如：the king of night
case "nmod:to": //to关系，例如：go to school, came to party
case "nmod:into": //名词修饰短语，例如：Investigation into the cause of the collision
case "nmod:for": //for关系名词修饰短语, vehicle inspections for damage assessment
case "compound": //multiword expression (MVE)形式
case "advmod": //副词修饰 safely anchored
modifiers.Add((dep.dep(), relationType));
break;
}
;
}
return(modifiers);
}