/// <summary>
/// Creates events for the provided sample.
/// </summary>
/// <param name="sample">The sample the sample for which training <see cref="T:Event"/>s are be created.</param>
/// <returns>The events enumerator.</returns>
protected override IEnumerator <Event> CreateEvents(NameSample sample)
{
if (sample.ClearAdaptiveData)
{
contextGenerator.ClearAdaptiveData();
}
var tokens = new string[sample.Sentence.Length];
var outcomes = codec.Encode(sample.Names, tokens.Length);
additionalContextFeatureGenerator.SetCurrentContext(sample.AdditionalContext);
for (int i = 0; i < sample.Sentence.Length; i++)
{
tokens[i] = sample.Sentence[i];
}
return(GenerateEvents(tokens, outcomes, contextGenerator).GetEnumerator());
}
/// <summary>
/// Generates name tags for the given sequence, typically a sentence, returning token spans for any identified names.
/// </summary>
/// <param name="tokens">An array of the tokens or words of the sequence, typically a sentence.</param>
/// <param name="additionalContext">Features which are based on context outside of the sentence but which should also be used.</param>
/// <returns>An array of spans for each of the names identified.</returns>
public Span[] Find(string[] tokens, string[][] additionalContext)
{
additionalContextFeatureGenerator.SetCurrentContext(additionalContext);
bestSequence = model.BestSequence(tokens,
Array.ConvertAll(additionalContext, input => (object)input),
contextGenerator,
sequenceValidator);
var outcomes = bestSequence.Outcomes.ToArray();
contextGenerator.UpdateAdaptiveData(tokens, outcomes);
var spans = sequenceCodec.Decode(outcomes);
var probs = Probs(spans);
for (var i = 0; i < probs.Length; i++)
{
spans[i].Probability = probs[i];
}
return(spans);
}
