Instance Constructors
-
new
ForwardPosTagger(url: URL)
-
new
ForwardPosTagger(file: File)
-
new
ForwardPosTagger(stream: InputStream)
-
new
ForwardPosTagger()
Value Members
-
final
def
!=(arg0: AnyRef): Boolean
-
final
def
!=(arg0: Any): Boolean
-
final
def
##(): Int
-
final
def
==(arg0: AnyRef): Boolean
-
final
def
==(arg0: Any): Boolean
-
-
-
def
accuracy(sentences: Iterable[Sentence]): (Double, Double, Double, Double)
-
final
def
asInstanceOf[T0]: T0
-
def
clone(): AnyRef
-
def
deserialize(stream: InputStream): Unit
-
def
deserialize(file: File): Unit
-
def
documentAnnotationString(document: Document): String
-
final
def
eq(arg0: AnyRef): Boolean
-
def
equals(arg0: Any): Boolean
-
var
exampleSetsToPrediction: Boolean
-
-
-
def
finalize(): Unit
-
final
def
getClass(): Class[_]
-
def
hashCode(): Int
-
final
def
isInstanceOf[T0]: Boolean
-
-
def
lemmatize(string: String): String
-
def
mentionAnnotationString(mention: Mention): String
-
-
final
def
ne(arg0: AnyRef): Boolean
-
final
def
notify(): Unit
-
final
def
notifyAll(): Unit
-
def
phraseAnnotationString(phrase: Phrase): String
-
def
postAttrs: Iterable[Class[_]]
-
def
predict(document: Document): Unit
-
def
predict(span: TokenSpan): Unit
-
def
predict(tokens: Seq[Token]): Unit
-
def
prereqAttrs: Iterable[Class[_]]
-
def
printAccuracy(sentences: Iterable[Sentence], extraText: String): Unit
-
-
-
-
-
def
serialize(stream: OutputStream): Unit
-
def
serialize(filename: String): Unit
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
-
-
def
toString(): String
-
def
tokenAnnotationString(token: Token): String
-
def
train(trainSentences: Seq[Sentence], testSentences: Seq[Sentence], lrate: Double = 0.1, decay: Double = 0.01, cutoff: Int = 2, doBootstrap: Boolean = true, useHingeLoss: Boolean = false, numIterations: Int = 5, l1Factor: Double = 0.000001, l2Factor: Double = 0.000001)(implicit random: Random): Unit
-
final
def
wait(): Unit
-
final
def
wait(arg0: Long, arg1: Int): Unit
-
final
def
wait(arg0: Long): Unit
A part-of-speech tagger that predicts by greedily labeling each word in sequence. Although it does not use Viterbi, it is surprisingly accurate. It is also fast.
For the Viterbi-based part-of-speech tagger, see ChainPosTagger.