public void TestDecode()
{
var decoder = new CRFDecoder();
var options = new DecoderOptions
{
ModelFileName = @"C:\Users\haipi\Documents\Projects\BotSharp\Data\CRF\ner_model"
};
//Load encoded model from file
decoder.LoadModel(options.ModelFileName);
//Create decoder tagger instance.
var tagger = decoder.CreateTagger(options.NBest, options.MaxWord);
tagger.set_vlevel(options.ProbLevel);
//Initialize result
var crf_out = new CRFSegOut[options.NBest];
for (var i = 0; i < options.NBest; i++)
{
crf_out[i] = new CRFSegOut(options.MaxWord);
}
var dataset = GetTestData();
//predict given string's tags
decoder.Segment(crf_out, tagger, dataset);
}
public async Task <bool> Predict(AgentBase agent, NlpDoc doc, PipeModel meta)
{
var decoder = new CRFDecoder();
var options = new DecoderOptions
{
ModelFileName = System.IO.Path.Combine(Settings.ModelDir, meta.Model)
};
//Load encoded model from file
decoder.LoadModel(options.ModelFileName);
//Create decoder tagger instance.
var tagger = decoder.CreateTagger(options.NBest, options.MaxWord);
tagger.set_vlevel(options.ProbLevel);
//Initialize result
var crf_out = new CRFSegOut[options.NBest];
for (var i = 0; i < options.NBest; i++)
{
crf_out[i] = new CRFSegOut(options.MaxWord);
}
doc.Sentences.ForEach(sent =>
{
List <List <String> > dataset = new List <List <string> >();
dataset.AddRange(sent.Tokens.Select(token => new List <String> {
token.Text, token.Pos
}).ToList());
//predict given string's tags
decoder.Segment(crf_out, tagger, dataset);
var entities = new List <NlpEntity>();
for (int i = 0; i < sent.Tokens.Count; i++)
{
var entity = crf_out[0].result_;
entities.Add(new NlpEntity
{
Entity = entity[i],
Start = doc.Sentences[0].Tokens[i].Start,
Value = doc.Sentences[0].Tokens[i].Text,
Confidence = 0,
Extrator = "BotSharpNER"
});
}
sent.Entities = MergeEntity(doc.Sentences[0].Text, entities);
});
return(true);
}
