/// <summary>
/// 聚类算法，用来匹配表
/// </summary>
/// <param name="matchProperty"></param>
/// <param name="original"></param>
/// <param name="target"></param>
public IScenarioFactor ClusterFactor(string matchProperty, string original, string target)
{
//1.根据matchPropery类型，设置matchKey, 这里先假定为 original (subject)
string fieldKey = original;
Dictionary <float?, IScenarioFactor> dict = new Dictionary <float?, IScenarioFactor>();
//逐个与表的匹配字段进行对比
_factors.ForEach((fr) =>
{
var(p, f) = IntersectProbability(fr as BaseScenarioFactor, fieldKey);
dict[p] = f;
});
//聚类可视化
//排序，找到合适的属性
float?key = dict.Keys.ToList().OrderBy(o => o).Where(o => o > CONFIDENCE).ToList()?.FirstOrDefault();
if (key == null)
{
return(null);
}
//寻找合适的类型
IScenarioFactor factor = dict[key];
return(factor);
}
/// <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>
/// MergeValue
/// </summary>
/// <param name="matchProperty"></param>
/// <param name="subject"></param>
/// <param name="value"></param>
public void MergeValue(string matchProperty, string subject, string value, IScenarioFactor fa)
{
foreach (string propertyName in fa.Properties)
{
float[] mv = _net.ToFloat(subject);
float[] pv = _net.ToFloat(propertyName.ToLower());
float p = NP.Cosine(mv, pv);
//为属性设置值
if (p > CONFIDENCE)
{
fa.SetPerperty(propertyName, value);
}
}
}
/// <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);
}
}
