csli.util.nlp.lemma
Class DictionaryLemmatiser

java.lang.Object
  csli.util.nlp.Lemmatiser
      csli.util.nlp.lemma.DictionaryLemmatiser

All Implemented Interfaces:

Serializable

public class DictionaryLemmatiser
extends Lemmatiser

Dictionary-based lemmatiser - loads morphological variant lists from a dictionary file into a lookup table. Rule files should be in /util/ext - there's one called oald_penn_morph_lists.txt derived from the Oxford Advanced Learner's Dictionary of English and using the Penn Treebank PoS tagset.

Author:

mpurver

See Also:

Serialized Form

Constructor Summary

DictionaryLemmatiser()

Method Summary

Lemma	getLemma(String wordString) Produce a lemma (pair of root form & part-of-speech) from a word string.
String	getWord(Lemma lemma) Generate a morphological word string from a lemma (pair of root form & part-of-speech).
static void	main(String[] args)

Methods inherited from class csli.util.nlp.Lemmatiser

getLemma, getWord

Methods inherited from class java.lang.Object

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

Constructor Detail

DictionaryLemmatiser

public DictionaryLemmatiser()

Method Detail

getLemma

public Lemma getLemma(String wordString)

Description copied from class: Lemmatiser

Produce a lemma (pair of root form & part-of-speech) from a word string. Should return NULL on error.

Specified by:

getLemma in class Lemmatiser

Parameters:

wordString - the word string to lemmatise

Returns:

the corresponding lemma

getWord

public String getWord(Lemma lemma)

Description copied from class: Lemmatiser

Generate a morphological word string from a lemma (pair of root form & part-of-speech). Should return NULL on error.

Specified by:

getWord in class Lemmatiser

Parameters:

lemma - the lemma from which to generate

Returns:

the corresponding word string

main

public static void main(String[] args)