eus.ixa.ixa.pipe.lemma

Class StatisticalLemmatizer

java.lang.Object

eus.ixa.ixa.pipe.lemma.StatisticalLemmatizer

public class StatisticalLemmatizer
extends Object

Probabilistic lemmatizer.

Version:

2016-01-28

Author:

ragerri

Constructor Summary

Constructors

Constructor and Description
StatisticalLemmatizer(Properties props) Construct a statistical lemmatizer.
StatisticalLemmatizer(Properties props, MorphoFactory aMorphoFactory) Construct a statistical lemmatizer with MorphoFactory.

Method Summary

Modifier and Type	Method and Description
List<Morpheme>	getMorphemes(String[] tokens, String[] posTags) Get lemmas from a tokenized and pos tagged sentence.
List<Morpheme>	getMorphemesFromStrings(String[] tokens, String[] posTags, List<String> lemmas) Create Morpheme objects from the output of posAnnotate.
List<String>	lemmatize(String[] tokens, String[] posTags) Produce lemmas from a tokenized sentence and its postags.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

StatisticalLemmatizer

public StatisticalLemmatizer(Properties props)

Construct a statistical lemmatizer.

Parameters:

props - the properties object

StatisticalLemmatizer

public StatisticalLemmatizer(Properties props,
                             MorphoFactory aMorphoFactory)

Construct a statistical lemmatizer with MorphoFactory.

Parameters:

props - the properties object

aMorphoFactory - the morpho factory

Method Detail

getMorphemes

public final List<Morpheme> getMorphemes(String[] tokens,
                                         String[] posTags)

Get lemmas from a tokenized and pos tagged sentence.

Parameters:

tokens - the tokenized sentence

posTags - the pos tags of the sentence

Returns:

a list of Morpheme objects containing morphological info

lemmatize

public List<String> lemmatize(String[] tokens,
                              String[] posTags)

Produce lemmas from a tokenized sentence and its postags.

Parameters:

tokens - the tokens

posTags - the pos tags

Returns:

the lemmas

getMorphemesFromStrings

public final List<Morpheme> getMorphemesFromStrings(String[] tokens,
                                                    String[] posTags,
                                                    List<String> lemmas)

Create Morpheme objects from the output of posAnnotate.

Parameters:

tokens - the tokens

posTags - the postags

lemmas - the lemmas

Returns:

a list of morpheme objects