edu.stanford.nlp.parser.lexparser
Class GermanUnknownWordModel
java.lang.Object
edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel
edu.stanford.nlp.parser.lexparser.GermanUnknownWordModel
- All Implemented Interfaces:
- UnknownWordModel, Serializable
public class GermanUnknownWordModel
- extends BaseUnknownWordModel
An unknown word model for German; relies on BaseUnknownWordModel plus number matching.
An assumption of this model is that numbers (arabic digit sequences)
are tagged CARD. This is correct for all of NEGRA/Tiger/TuebaDZ.
- Author:
- Roger Levy, Greg Donaker (corrections and modeling improvements), Christopher Manning (generalized and improved what Greg did)
- See Also:
- Serialized Form
Method Summary |
float |
score(IntTaggedWord itw)
Calculate the log-prob score of a particular TaggedWord in the
unknown word model. |
Methods inherited from class edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel |
addTagging, getLexicon, getSignature, getSignatureIndex, getUnknownLevel, score, scoreGT, setUnknownLevel, train, trainUnknownGT, unSeenCounter |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
GermanUnknownWordModel
public GermanUnknownWordModel(Options.LexOptions op,
Lexicon lex)
score
public float score(IntTaggedWord itw)
- Calculate the log-prob score of a particular TaggedWord in the
unknown word model.
- Overrides:
score
in class BaseUnknownWordModel
- Parameters:
itw
- the tag->word production in IntTaggedWord form
- Returns:
- The log-prob score of a particular TaggedWord.
Stanford NLP Group