Tagger/desc/HmmTagger.xml (130 lines of code) (raw):

<?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.HMMTagger</annotatorImplementationName> <analysisEngineMetaData> <name>Hidden Markov Model - Part of Speech Tagger</name> <description>A configuration of the HmmTaggerAnnotator that looks for parts of speech of identified tokens within existing Sentence and Token annotations. See also WhitespaceTokenizer.xml.</description> <version>1.0</version> <vendor>The Apache Software Foundation</vendor> <configurationParameters> <configurationParameter> <name>NGRAM_SIZE</name> <type>Integer</type> <multiValued>false</multiValued> <mandatory>true</mandatory> </configurationParameter> <configurationParameter> <name>InputView</name> <description>Name of the parameter for the input view (by default it is set to _InitialView)</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>SentenceType</name> <description>Sentence annotation type which covers token annotations (by default it is set to org.apache.uima.SentenceAnnotation)</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>TokenFeaturePath</name> <description>Token feature path to set. It should be like "type.name:attribute" (set by default to "org.apache.uima.TokenAnnotation:posTag")</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>ModelFile</name> <description>If the resource model file is not set, this parameter can be used. If both are empty, the system will throw an exception.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> </configurationParameters> <configurationParameterSettings> <nameValuePair> <name>NGRAM_SIZE</name> <value> <integer>3</integer> </value> </nameValuePair> </configurationParameterSettings> <typeSystemDescription> <types> <typeDescription> <name>org.apache.uima.TokenAnnotation</name> <description>Single token annotation</description> <supertypeName>uima.tcas.Annotation</supertypeName> <features> <featureDescription> <name>posTag</name> <description>contains part-of-speech of a corresponding token</description> <rangeTypeName>uima.cas.String</rangeTypeName> </featureDescription> </features> </typeDescription> <typeDescription> <name>org.apache.uima.SentenceAnnotation</name> <description>sentence annotation</description> <supertypeName>uima.tcas.Annotation</supertypeName> </typeDescription> </types> </typeSystemDescription> <typePriorities/> <fsIndexCollection/> <capabilities> <capability> <inputs> <type>org.apache.uima.TokenAnnotation</type> <type allAnnotatorFeatures="true">org.apache.uima.SentenceAnnotation</type> <feature>org.apache.uima.TokenAnnotation:end</feature> <feature>org.apache.uima.TokenAnnotation:begin</feature> </inputs> <outputs> <type>org.apache.uima.TokenAnnotation</type> <feature>org.apache.uima.TokenAnnotation:posTag</feature> <feature>org.apache.uima.TokenAnnotation:end</feature> <feature>org.apache.uima.TokenAnnotation:begin</feature> </outputs> <languagesSupported/> </capability> </capabilities> <operationalProperties> <modifiesCas>true</modifiesCas> <multipleDeploymentAllowed>true</multipleDeploymentAllowed> <outputsNewCASes>false</outputsNewCASes> </operationalProperties> </analysisEngineMetaData> <externalResourceDependencies> <externalResourceDependency> <key>Model</key> <description>HMM Tagger model file</description> <interfaceName>org.apache.uima.examples.tagger.IModelResource</interfaceName> <optional>false</optional> </externalResourceDependency> </externalResourceDependencies> <resourceManagerConfiguration> <externalResources> <externalResource> <name>ModelFile</name> <description>HMM Tagger model file</description> <fileResourceSpecifier> <fileUrl>file:english/BrownModel.dat</fileUrl> </fileResourceSpecifier> <implementationName>org.apache.uima.examples.tagger.ModelResource</implementationName> </externalResource> </externalResources> <externalResourceBindings> <externalResourceBinding> <key>Model</key> <resourceName>ModelFile</resourceName> </externalResourceBinding> </externalResourceBindings> </resourceManagerConfiguration> </analysisEngineDescription>