/// <summary> /// Generates chunk tags for the given sequence returning the result in an array. /// </summary> /// <param name="tokens">an array of the tokens or words of the sequence.</param> /// <param name="tags">an array of the pos tags of the sequence.</param> /// <returns>An array of chunk tags for each token in the sequence or a <c>null</c> value if none.</returns> /// <exception cref="System.ArgumentNullException"> /// The <paramref name="tokens"/> is null. /// or /// The <paramref name="tags"/> is null. /// </exception> /// <exception cref="System.ArgumentOutOfRangeException">The token array is empty.</exception> public string[] Chunk(string[] tokens, string[] tags) { if (tokens == null) { throw new ArgumentNullException("tokens"); } if (tokens.Length == 0) { throw new ArgumentOutOfRangeException("tokens", "The token array is empty."); } if (tags == null) { throw new ArgumentNullException("tags"); } bestSequence = model.BestSequence(tokens, new object[] { tags }, contextGenerator, sequenceValidator); return(bestSequence == null ? null : bestSequence.Outcomes.ToArray()); }
/// <summary> /// Returns the lemma of the specified word with the specified part-of-speech. /// </summary> /// <param name="tokens">An array of the tokens.</param> /// <param name="tags">An array of the POS tags.</param> /// <returns>An array of lemma classes for each token in the sequence.</returns> /// <exception cref="ArgumentNullException"><paramref name="tokens" /> or <paramref name="tags" /></exception> /// <exception cref="ArgumentException">The arguments must have the same length.</exception> public string[] Lemmatize(string[] tokens, string[] tags) { if (tokens == null) { throw new ArgumentNullException(nameof(tokens)); } if (tags == null) { throw new ArgumentNullException(nameof(tags)); } if (tokens.Length != tags.Length) { throw new ArgumentException("The arguments must have the same length."); } bestSequence = model.BestSequence(tokens, new object[] { tags }, contextGenerator, sequenceValidator); return(bestSequence.Outcomes.ToArray()); }
/// <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); }
/// <summary> /// Generates chunk tags for the given sequence returning the result in an array. /// </summary> /// <param name="tokens">an array of the tokens or words of the sequence.</param> /// <param name="tags">an array of the pos tags of the sequence.</param> /// <returns>an array of chunk tags for each token in the sequence.</returns> public string[] Chunk(string[] tokens, string[] tags) { bestSequence = model.BestSequence(tokens, new object[] { tags }, contextGenerator, sequenceValidator); return(bestSequence.Outcomes.ToArray()); }
/// <summary> /// Assigns the sentence of tokens pos tags. /// </summary> /// <param name="sentence">The sentence of tokens to be tagged.</param> /// <param name="additionalContext">Any addition context specific to a class implementing this interface.</param> /// <returns>an array of pos tags for each token provided in sentence.</returns> public string[] Tag(string[] sentence, object[] additionalContext) { bestSequence = model.BestSequence(sentence, additionalContext, ContextGenerator, SequenceValidator); return(bestSequence.Outcomes.ToArray()); }