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, java.io.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
Fields inherited from class edu.stanford.nlp.parser.lexparser.BaseUnknownWordModel |
NULL_ITW, nullTag, nullWord, tagHash, tagIndex, trainOptions, unknown, unknownLevel, unSeenCounter, useFirst, useGT, VERBOSE, wordIndex |
Constructor Summary |
GermanUnknownWordModel(Options op,
Lexicon lex,
Index<java.lang.String> wordIndex,
Index<java.lang.String> tagIndex)
This constructor creates an UWM with empty data structures. |
GermanUnknownWordModel(Options op,
Lexicon lex,
Index<java.lang.String> wordIndex,
Index<java.lang.String> tagIndex,
ClassicCounter<IntTaggedWord> unSeenCounter,
java.util.Map<Label,ClassicCounter<java.lang.String>> tagHash,
java.util.Map<java.lang.String,java.lang.Float> unknownGT,
java.util.Set<java.lang.String> seenEnd)
|
Method Summary |
float |
score(IntTaggedWord itw,
java.lang.String word)
Calculate the log-prob score of a particular TaggedWord in the
unknown word model. |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
GermanUnknownWordModel
public GermanUnknownWordModel(Options op,
Lexicon lex,
Index<java.lang.String> wordIndex,
Index<java.lang.String> tagIndex,
ClassicCounter<IntTaggedWord> unSeenCounter,
java.util.Map<Label,ClassicCounter<java.lang.String>> tagHash,
java.util.Map<java.lang.String,java.lang.Float> unknownGT,
java.util.Set<java.lang.String> seenEnd)
GermanUnknownWordModel
public GermanUnknownWordModel(Options op,
Lexicon lex,
Index<java.lang.String> wordIndex,
Index<java.lang.String> tagIndex)
- This constructor creates an UWM with empty data structures. Only
use if loading in the data separately, such as by reading in text
lines containing the data.
score
public float score(IntTaggedWord itw,
java.lang.String word)
- 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