public static List <NR> ViterbiCompute(List <TagFreqItem <NR> > tags) => Viterbi.Compute(tags, ChsPersonNameDict.transformMatrixDictionary);
public override List <Term> SegSentence(char[] sentence)
{
var list = new List <Term>();
if (sentence.Length == 0)
{
return(list);
}
var convertedChars = CharTable.Convert(sentence);
var table = new Table();
table.v = AtomSeg2Table(convertedChars);
_crfModel.Tag(table);
int offset = 0;
for (int i = 0; i < table.Size; offset += table.v[i][1].Length, i++)
{
var line = table.v[i];
switch (line[2][0])
{
case 'B':
int begin = offset;
while (table.v[i][2][0] != 'E') // 寻找结束标签'E'
{
offset += table.v[i][1].Length;
i++;
if (i == table.Size)
{
break; // 达到最后一个字符
}
}
// 退出while循环
if (i == table.Size) // 肯定是由while loop的break退出的，offset已经包含了最后一格词的长度
{
list.Add(new Term(new string(sentence, begin, offset - begin), Nature.none));
}
else // 由while loop正常退出，当前词标注为'E',offset尚未包含这个词的长度
{
list.Add(new Term(new string(sentence, begin, offset - begin + table.v[i][1].Length), Nature.none));
}
break;
default: // 理论来说，只可能是标注为'S'，所以单独成词
list.Add(new Term(new string(sentence, offset, table.v[i][1].Length), Nature.none));
break;
}
}
if (config.natureTagging)
{
var vertices = ToVertexList(list, true);
Viterbi.Compute(vertices, CoreDictTransfromMatrixDictionary.transformMatrixDictionary);
for (int i = 0; i < list.Count; i++)
{
var term = list[i];
if (term.nature == Nature.none)
{
term.nature = vertices[i + 1].GuessNature(); // vertices[i+1] -> 附加了辅助起始节点
}
}
}
if (config.useCustomDict)
{
var vertices = ToVertexList(list, false); //? 会不会覆盖上面的词性标注值
CombineByCustomDict(vertices);
list = ToTermList(vertices, config.offset);
}
return(list);
}
public static List <NS> ViterbiExCompute(List <TagFreqItem <NS> > roleTagList) => Viterbi.Compute(roleTagList, PlaceDictionary.trans_tr_dict);
/// <summary> /// 词性标注 /// </summary> /// <param name="list"></param> public static void SpeechTaggint(List <Vertex> list) => Viterbi.Compute(list, CoreDictTransfromMatrixDictionary.transformMatrixDictionary);
/// <summary> /// 维特比算法求解最优标签 /// </summary> /// <param name="roleTagList"></param> /// <returns></returns> public static List <NT> ViterbiExCompute(List <TagFreqItem <NT> > roleTagList) => Viterbi.Compute(roleTagList, OrgDictionary.transformMatrixDictionary);
