/// <summary>
/// Attempt to infer the part of speech of the given preterminal node, which
/// was created during the expansion of a multi-word token.
/// </summary>
private static string InferPOS(Tree t, Tree parent, TwoDimensionalCounter <string, string> unigramTagger)
{
string word = t.FirstChild().Value();
string containingPhraseStr = GetContainingPhrase(t, parent);
// Overrides: let the manual POS model handle a few special cases first
string overrideTag = MultiWordPreprocessor.ManualUWModel.GetOverrideTag(word, containingPhraseStr);
if (overrideTag != null)
{
return(overrideTag);
}
ICollection <string> unigramTaggerKeys = unigramTagger.FirstKeySet();
// Try treating this word as a verb and stripping any clitic
// pronouns. If the stripped version exists in the unigram
// tagger, then stick with the verb hypothesis
SpanishVerbStripper.StrippedVerb strippedVerb = verbStripper.SeparatePronouns(word);
if (strippedVerb != null && unigramTaggerKeys.Contains(strippedVerb.GetStem()))
{
string pos = Counters.Argmax(unigramTagger.GetCounter(strippedVerb.GetStem()));
if (pos.StartsWith("v"))
{
return(pos);
}
}
if (unigramTagger.FirstKeySet().Contains(word))
{
return(Counters.Argmax(unigramTagger.GetCounter(word), new MultiWordPreprocessor.POSTieBreaker()));
}
return(MultiWordPreprocessor.ManualUWModel.GetTag(word, containingPhraseStr));
}
/// <summary>
/// Handles verbs with attached suffixes, marked by the lexer:
/// Escribamosela => Escribamo + se + la => escribamos + se + la
/// Sentaos => senta + os => sentad + os
/// Damelo => da + me + lo
/// </summary>
private CoreLabel ProcessVerb(CoreLabel cl)
{
cl.Remove(typeof(CoreAnnotations.ParentAnnotation));
SpanishVerbStripper.StrippedVerb stripped = verbStripper.SeparatePronouns(cl.Word());
if (stripped == null)
{
return(cl);
}
// Split the CoreLabel into separate labels, tracking changing begin + end
// positions.
int stemEnd = cl.BeginPosition() + stripped.GetOriginalStem().Length;
int lengthRemoved = 0;
foreach (string pronoun in stripped.GetPronouns())
{
int beginOffset = stemEnd + lengthRemoved;
compoundBuffer.Add(CopyCoreLabel(cl, pronoun, beginOffset));
lengthRemoved += pronoun.Length;
}
CoreLabel stem = CopyCoreLabel(cl, stripped.GetStem(), cl.BeginPosition(), stemEnd);
stem.SetOriginalText(stripped.GetOriginalStem());
return(stem);
}
/// <summary>
/// Determine whether the given clitic pronoun is an indirect object
/// pronoun or a reflexive pronoun.
/// </summary>
/// <remarks>
/// Determine whether the given clitic pronoun is an indirect object
/// pronoun or a reflexive pronoun.
/// This method is only defined when the pronoun is one of
/// me, te, se, nos, os
/// i.e., those in which the meaning is actually ambiguous.
/// </remarks>
/// <param name="strippedVerb">
/// Stripped verb as returned by
/// <see cref="Edu.Stanford.Nlp.International.Spanish.SpanishVerbStripper.SeparatePronouns(string)"/>
/// .
/// </param>
/// <param name="pronounIdx">
/// The index of the pronoun within
/// <c>strippedVerb.getPronouns()</c>
/// which should be
/// disambiguated.
/// </param>
/// <param name="clauseYield">
/// A string representing the yield of the
/// clause which contains the given verb
/// </param>
/// <exception cref="System.ArgumentException">
/// If the given pronoun is
/// not ambiguous, or its disambiguation is not supported.
/// </exception>
public static AnCoraPronounDisambiguator.PersonalPronounType DisambiguatePersonalPronoun(SpanishVerbStripper.StrippedVerb strippedVerb, int pronounIdx, string clauseYield)
{
IList <string> pronouns = strippedVerb.GetPronouns();
string pronoun = pronouns[pronounIdx].ToLower();
if (!ambiguousPersonalPronouns.Contains(pronoun))
{
throw new ArgumentException("We don't support disambiguating pronoun '" + pronoun + "'");
}
if (pronouns.Count == 1 && Sharpen.Runtime.EqualsIgnoreCase(pronoun, "se"))
{
return(AnCoraPronounDisambiguator.PersonalPronounType.Reflexive);
}
string verb = strippedVerb.GetStem();
if (alwaysReflexiveVerbs.Contains(verb))
{
return(AnCoraPronounDisambiguator.PersonalPronounType.Reflexive);
}
else
{
if (neverReflexiveVerbs.Contains(verb))
{
return(AnCoraPronounDisambiguator.PersonalPronounType.Object);
}
}
Pair <string, string> bruteForceKey = new Pair <string, string>(verb, clauseYield);
if (bruteForceDecisions.Contains(bruteForceKey))
{
return(bruteForceDecisions[bruteForceKey]);
}
// Log this instance where a clitic pronoun could not be disambiguated.
log.Info("Failed to disambiguate: " + verb + "\nContaining clause:\t" + clauseYield + "\n");
return(AnCoraPronounDisambiguator.PersonalPronounType.Unknown);
}
