public override CoNLLSentence Parse(List <Term> terms)
{
var table = new Table();
table.v = new string[terms.Count][];
for (int i = 0; i < terms.Count; i++)
{
var term = terms[i];
var line = new string[4];
table.v[i] = line;
line[0] = term.word;
line[2] = DependencyUtil.compilePOS(term.nature);
line[1] = line[2].Substring(0, 1);
}
_crfModel.Tag(table);
var words = new CoNLLWord[table.Size];
for (int i = 0; i < words.Length; i++)
{
words[i] = new CoNLLWord(i + 1, table.v[i][0], table.v[i][2], table.v[i][1]);
}
for (int i = 0; i < table.Size; i++)
{
var line = table.v[i];
var dtag = new DTag(line[3]);
if (dtag.pos.EndsWith("ROOT"))
{
words[i].HEAD = CoNLLWord.ROOT;
}
else
{
var index = ConvertOffset2Index(dtag, table, i);
if (index == -1)
{
words[i].HEAD = CoNLLWord.NULL;
}
else
{
words[i].HEAD = words[index];
}
}
}
for (int i = 0; i < words.Length; i++)
{
words[i].DEPREL = BigramDependencyModel.Get(words[i].NAME, words[i].POSTAG, words[i].HEAD.NAME, words[i].HEAD.POSTAG);
}
return(new CoNLLSentence(words));
}
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);
}
