public SegDecoderTagger CreateTagger(int nbest, int this_crf_max_word_num = Utils.DEFAULT_CRF_MAX_WORD_NUM)
{
if (modelReader == null)
{
return null;
}
var tagger = new SegDecoderTagger(nbest, this_crf_max_word_num);
tagger.init_by_model(modelReader);
return tagger;
}
public SegDecoderTagger CreateTagger(int nbest)
{
if (modelReader == null)
{
return(null);
}
SegDecoderTagger tagger = new SegDecoderTagger(nbest);
tagger.init_by_model(modelReader);
return(tagger);
}
public SegDecoderTagger CreateTagger(int nbest, int this_crf_max_word_num = Utils.DEFAULT_CRF_MAX_WORD_NUM)
{
if (modelReader == null)
{
return(null);
}
SegDecoderTagger tagger = new SegDecoderTagger(nbest, this_crf_max_word_num);
tagger.init_by_model(modelReader);
return(tagger);
}
//Segment given text
public int Segment(crf_seg_out[] pout, //segment result
SegDecoderTagger tagger, //Tagger per thread
List <List <string> > inbuf //feature set for segment
)
{
int ret = 0;
if (inbuf.Count == 0)
{
//Empty input string
return(Utils.ERROR_SUCCESS);
}
ret = tagger.reset();
if (ret < 0)
{
return(ret);
}
ret = tagger.add(inbuf);
if (ret < 0)
{
return(ret);
}
//parse
ret = tagger.parse();
if (ret < 0)
{
return(ret);
}
//wrap result
ret = tagger.output(pout);
if (ret < 0)
{
return(ret);
}
return(Utils.ERROR_SUCCESS);
}
//Segment given text
public int Segment(crf_seg_out[] pout, //segment result
SegDecoderTagger tagger, //Tagger per thread
List<List<string>> inbuf //feature set for segment
)
{
var ret = 0;
if (inbuf.Count == 0)
{
//Empty input string
return Utils.ERROR_SUCCESS;
}
ret = tagger.reset();
if (ret < 0)
{
return ret;
}
ret = tagger.add(inbuf);
if (ret < 0)
{
return ret;
}
//parse
ret = tagger.parse();
if (ret < 0)
{
return ret;
}
//wrap result
ret = tagger.output(pout);
if (ret < 0)
{
return ret;
}
return Utils.ERROR_SUCCESS;
}
//Output raw result with probability
private void OutputRawResultToFile(List<List<string>> inbuf, crf_term_out[] crf_out, SegDecoderTagger tagger, StreamWriter sw)
{
for (var k = 0; k < crf_out.Length; k++)
{
if (crf_out[k] == null)
{
//No more result
break;
}
var sb = new StringBuilder();
var crf_seg_out = crf_out[k];
//Show the entire sequence probability
//For each token
for (var i = 0; i < inbuf.Count; i++)
{
//Show all features
for (var j = 0; j < inbuf[i].Count; j++)
{
sb.Append(inbuf[i][j]);
sb.Append("\t");
}
//Show the best result and its probability
sb.Append(crf_seg_out.result_[i]);
if (tagger.vlevel_ > 1)
{
sb.Append("\t");
sb.Append(crf_seg_out.weight_[i]);
//Show the probability of all tags
sb.Append("\t");
for (var j = 0; j < tagger.ysize_; j++)
{
sb.Append(tagger.yname(j));
sb.Append("/");
sb.Append(tagger.prob(i, j));
if (j < tagger.ysize_ - 1)
{
sb.Append("\t");
}
}
}
sb.AppendLine();
}
if (tagger.vlevel_ > 0)
{
sw.WriteLine("#{0}", crf_seg_out.prob);
}
sw.WriteLine(sb.ToString().Trim());
sw.WriteLine();
}
}
//Output raw result with probability
private void OutputRawResultToFile(List <List <string> > inbuf, crf_term_out[] crf_out, SegDecoderTagger tagger, StreamWriter sw)
{
foreach (crf_term_out crf_seg_out in crf_out)
{
if (crf_seg_out == null)
{
//No more result
break;
}
var sb = new StringBuilder();
//Show the entire sequence probability
//For each token
for (var i = 0; i < inbuf.Count; i++)
{
//Show all features
for (var j = 0; j < inbuf[i].Count; j++)
{
sb.Append(inbuf[i][j]);
sb.Append("\t");
}
//Show the best result and its probability
sb.Append(crf_seg_out.result_[i]);
if (tagger.vlevel_ > 1)
{
sb.Append("\t");
sb.Append(crf_seg_out.weight_[i]);
//Show the probability of all tags
sb.Append("\t");
for (var j = 0; j < tagger.ysize_; j++)
{
sb.Append(tagger.yname(j));
sb.Append("/");
sb.Append(tagger.prob(i, j));
if (j < tagger.ysize_ - 1)
{
sb.Append("\t");
}
}
}
sb.AppendLine();
}
if (tagger.vlevel_ > 0)
{
sw.WriteLine("#{0}", crf_seg_out.prob);
}
sw.WriteLine(sb.ToString().Trim());
sw.WriteLine();
}
}
