This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch NLPCRAFT-520
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-520 by this push:
new c9cffb87 WIP
c9cffb87 is described below
commit c9cffb8746261ae8e1bbc7b322c7a9b047d65d78
Author: Aaron Radzinski <[email protected]>
AuthorDate: Tue Dec 13 13:49:37 2022 -0800
WIP
---
.../main/scala/org/apache/nlpcraft/nlp/stemmer/NCEnStemmer.scala | 6 +++---
.../src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCStemmer.scala | 7 +++++--
2 files changed, 8 insertions(+), 5 deletions(-)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCEnStemmer.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCEnStemmer.scala
index 7c4bed23..cf0dd30d 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCEnStemmer.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCEnStemmer.scala
@@ -21,9 +21,9 @@ import opennlp.tools.stemmer.PorterStemmer
import org.apache.nlpcraft.nlp.parsers.*
/**
- * English language [[NCStemmer]] implementation, based on
- * [[https://opennlp.apache.org/ OpenNLP]] Porter Stemmer.
- * Look more [[https://tartarus.org/martin/PorterStemmer here]].
+ * Stemmer implementation for the English language that delegates to
+ * [[https://opennlp.apache.org/ OpenNLP]] Porter Stemmer. You can find more
information about this
+ * stemmer algorithm at [[https://tartarus.org/martin/PorterStemmer]].
*/
class NCEnStemmer extends NCStemmer:
private val stemmer = new PorterStemmer
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCStemmer.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCStemmer.scala
index f57e580a..0009bab6 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCStemmer.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/stemmer/NCStemmer.scala
@@ -22,14 +22,17 @@ import org.apache.nlpcraft.nlp.parsers.*
/**
* Trait defining a general stemmer. Stemming is the process of reducing
inflected (or sometimes derived)
* words to their word stem, base or root form—generally a written word form.
Stemmer is used by some of the
- * built-in pipeline components.
+ * built-in pipeline components. Stemmer is used by several built-in pipeline
components.
*
* Read more about stemming at [[https://en.wikipedia.org/wiki/Stemming]].
+ *
+ * @see [[org.apache.nlpcraft.nlp.enrichers.NCEnStopWordsTokenEnricher]]
+ * @see [[NCSemanticEntityParser]]
*/
trait NCStemmer:
/**
* Gets a stem for a given text. Note that unlike lemma the
stemmatization process does not
- * require a context for the given word.
+ * require a context for the given word, i.e. the stemmatization can be
performed on individual word.
*
* @param word Text to stemmatize.
*/
