This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/master by this push:
new 1682a2af WIP.
1682a2af is described below
commit 1682a2afbe243084bc7e3398cf7885ded5537387
Author: Sergey Kamov <[email protected]>
AuthorDate: Wed Dec 7 17:28:09 2022 +0400
WIP.
---
.../nlpcraft/nlp/enrichers/NCEnSwearWordsTokenEnricher.scala | 2 +-
.../nlpcraft/nlp/enrichers/NCOpenNLPLemmaPosTokenEnricher.scala | 4 ++--
.../org/apache/nlpcraft/nlp/parsers/NCOpenNLPTokenParser.scala | 2 +-
.../scala/org/apache/nlpcraft/nlp/parsers/NCSemanticElement.scala | 1 +
.../org/apache/nlpcraft/nlp/parsers/NCSemanticEntityParser.scala | 7 +++++++
5 files changed, 12 insertions(+), 4 deletions(-)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCEnSwearWordsTokenEnricher.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCEnSwearWordsTokenEnricher.scala
index 27ad4a0e..4191b13c 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCEnSwearWordsTokenEnricher.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCEnSwearWordsTokenEnricher.scala
@@ -31,7 +31,7 @@ import java.util.Objects
* It adds <code>swear</code> boolean property to [[NCToken]] instance if
word which it represents is swear word.
*
* @param res Path to swear words list text resource.
- * Note that [[NCPipelineBuilder.withSemantic()]] methods use
+ * Note that [[NCPipelineBuilder.withSemantic()]] methods use for English
language
*
[[https://raw.githubusercontent.com/apache/incubator-nlpcraft/external_config/external/badfilter/swear_words.txt
NlpCraft Swearword Dictionary]]
*/
class NCEnSwearWordsTokenEnricher(res: String) extends NCTokenEnricher with
LazyLogging:
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCOpenNLPLemmaPosTokenEnricher.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCOpenNLPLemmaPosTokenEnricher.scala
index 82780458..d11e2641 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCOpenNLPLemmaPosTokenEnricher.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/enrichers/NCOpenNLPLemmaPosTokenEnricher.scala
@@ -38,10 +38,10 @@ import scala.concurrent.ExecutionContext
* Some of OpenNLP prepared models can be found
[[https://opennlp.sourceforge.net/models-1.5/ here]].
*
* @param posMdlSrc Path to
[[https://opennlp.apache.org/docs/2.0.0/apidocs/opennlp-tools/opennlp/tools/postag/POSTaggerME.html
POSTaggerME]] model.
- * Note that [[NCPipelineBuilder.withSemantic()]] methods use
[[http://opennlp.sourceforge.net/models-1.5/en-pos-maxent.bin
en-pos-maxent.bin]].
+ * Note that [[NCPipelineBuilder.withSemantic()]] methods use for English
language [[http://opennlp.sourceforge.net/models-1.5/en-pos-maxent.bin
en-pos-maxent.bin]].
*
* @param lemmaDicSrc Path to
[[https://opennlp.apache.org/docs/2.0.0/apidocs/opennlp-tools/opennlp/tools/lemmatizer/DictionaryLemmatizer.html
DictionaryLemmatizer]] model.
- * Note that [[NCPipelineBuilder.withSemantic()]] methods use
[[https://raw.githubusercontent.com/richardwilly98/elasticsearch-opennlp-auto-tagging/master/src/main/resources/models/en-lemmatizer.dict
en-lemmatizer.dict]].
+ * Note that [[NCPipelineBuilder.withSemantic()]] methods use for English
language
[[https://raw.githubusercontent.com/richardwilly98/elasticsearch-opennlp-auto-tagging/master/src/main/resources/models/en-lemmatizer.dict
en-lemmatizer.dict]].
*/
class NCOpenNLPLemmaPosTokenEnricher(posMdlSrc: String = null, lemmaDicSrc:
String = null) extends NCTokenEnricher with LazyLogging:
private var tagger: POSTaggerME = _
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCOpenNLPTokenParser.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCOpenNLPTokenParser.scala
index cbdbbea9..044e331d 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCOpenNLPTokenParser.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCOpenNLPTokenParser.scala
@@ -32,7 +32,7 @@ import java.util.Objects
* Some of OpenNLP prepared models can be found
[[https://opennlp.sourceforge.net/models-1.5/ here]].
*
* @param tokMdl Path to
[[https://opennlp.apache.org/docs/2.0.0/apidocs/opennlp-tools/opennlp/tools/tokenize/TokenizerModel.html
model]].
- * Note that [[NCPipelineBuilder.withSemantic()]] methods use
[[http://opennlp.sourceforge.net/models-1.5/en-token.bin
models-1.5/en-token.bin]].
+ * Note that [[NCPipelineBuilder.withSemantic()]] methods use for English
language [[http://opennlp.sourceforge.net/models-1.5/en-token.bin
en-token.bin]].
*/
class NCOpenNLPTokenParser(tokMdl: String) extends NCTokenParser with
LazyLogging:
require(tokMdl != null, "Tokenizer model path cannot be null.")
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticElement.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticElement.scala
index 621e35f1..0cbb408c 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticElement.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticElement.scala
@@ -37,6 +37,7 @@ package org.apache.nlpcraft.nlp.parsers
* <code>Semantic</code> implementation of
[[org.apache.nlpcraft.NCEntityParser NCEntityParser]].
*
* See detailed description
[[https://nlpcraft.apache.org/built-in-entity-parser.html#parser-semantic
Semantic Parser]].
+ *
* @see [[NCSemanticEntityParser]]
* @see [[NCSemanticStemmer]]
*/
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticEntityParser.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticEntityParser.scala
index 6dddf61d..d1cc8193 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticEntityParser.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/parsers/NCSemanticEntityParser.scala
@@ -180,6 +180,13 @@ import
org.apache.nlpcraft.nlp.parsers.NCSemanticEntityParser.*
* [[NCEntityParser]] built-in <code>semantic</code>implementation.
*
* See detailed description
[[https://nlpcraft.apache.org/built-in-entity-parser.html#parser-semantic
Semantic Parser]].
+ *
+ * Note that [[org.apache.nlpcraft.NCPipelineBuilder.withSemantic()
NCPipelineBuilder.withSemantic()]]
+ * methods use for English language
+ * [[org.apache.nlpcraft.nlp.parsers.NCOpenNLPTokenParser
NCOpenNLPTokenParser]] implementation of
+ * [[NCTokenParser]] with model
+ * [[http://opennlp.sourceforge.net/models-1.5/en-token.bin en-token.bin]].
+
*
* @see [[NCSemanticElement]]
* @see [[NCSemanticStemmer]]
