Tagger/desc/HmmModelTrainer.xml

<?xml version="1.0" encoding="UTF-8"?>
<!--
  Licensed to the Apache Software Foundation (ASF) under one
  or more contributor license agreements.  See the NOTICE file
  distributed with this work for additional information
  regarding copyright ownership.  The ASF licenses this file
  to you under the Apache License, Version 2.0 (the
  "License"); you may not use this file except in compliance
  with the License.  You may obtain a copy of the License at
  
  http://www.apache.org/licenses/LICENSE-2.0
  
  Unless required by applicable law or agreed to in writing,
  software distributed under the License is distributed on an
  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
  KIND, either express or implied.  See the License for the
  specific language governing permissions and limitations
  under the License.    
-->
<analysisEngineDescription xmlns="http://uima.apache.org/resourceSpecifier">
  <frameworkImplementation>org.apache.uima.java</frameworkImplementation>
  <primitive>true</primitive>
  <annotatorImplementationName>org.apache.uima.examples.tagger.HMMModelTrainer</annotatorImplementationName>
  <analysisEngineMetaData>
    <name>HMMModelTrainer</name>
    <description>This analysis engine trains an N-gram model for the HMM tagger. It uses a training corpus as reference. This corpus must contain annotations on words with an attribute corresponding of the POS value to be learned.

The configuration of this analysis engine is done through several parameters:
&lt;ul&gt;
&lt;li&gt;View: - the view from which the tokens will be extracted&lt;/li&gt;
&lt;li&gt;ModelExportFile: - the path where the model will be written&lt;/li&gt;
&lt;li&gt;FeaturePathPOS: - feature path to the value of the POS to be learned. The annotation should exactly cover a "word".&lt;/li&gt;
&lt;/ul&gt;

&lt;b&gt;BEWARE: this analysis engine does not allow multiple deployment !&lt;/b&gt;

&lt;i&gt;NB. At the moment: both bi and trigram statistics are saved in one model file.&lt;/i&gt;</description>
    <version>1.0</version>
    <vendor/>
    <configurationParameters>
      <configurationParameter>
        <name>View</name>
        <description>The view from which the tokens will be extracted.</description>
        <type>String</type>
        <multiValued>false</multiValued>
        <mandatory>true</mandatory>
      </configurationParameter>
      <configurationParameter>
        <name>ModelExportFile</name>
        <description>The path where the model will be written.</description>
        <type>String</type>
        <multiValued>false</multiValued>
        <mandatory>true</mandatory>
      </configurationParameter>
      <configurationParameter>
        <name>FeaturePathPOS</name>
        <description>Feature path to the value of the POS to be learnt. The annotation should exactly cover a "word".</description>
        <type>String</type>
        <multiValued>false</multiValued>
        <mandatory>true</mandatory>
      </configurationParameter>
    </configurationParameters>
    <configurationParameterSettings>
      <nameValuePair>
        <name>View</name>
        <value>
          <string>_InitialView</string>
        </value>
      </nameValuePair>
      <nameValuePair>
        <name>ModelExportFile</name>
        <value>
          <string>hmmtagger_model.dat</string>
        </value>
      </nameValuePair>
      <nameValuePair>
        <name>FeaturePathPOS</name>
        <value>
          <string>org.apache.uima.TokenAnnotation:posTag</string>
        </value>
      </nameValuePair>
    </configurationParameterSettings>
    <typeSystemDescription/>
    <typePriorities/>
    <fsIndexCollection/>
    <capabilities>
      <capability>
        <inputs/>
        <outputs/>
        <languagesSupported/>
      </capability>
    </capabilities>
    <operationalProperties>
      <modifiesCas>false</modifiesCas>
      <multipleDeploymentAllowed>false</multipleDeploymentAllowed>
      <outputsNewCASes>false</outputsNewCASes>
    </operationalProperties>
  </analysisEngineMetaData>
  <resourceManagerConfiguration/>
</analysisEngineDescription>