ctakes-dictionary-lookup-fast/desc/analysis_engine/UmlsOverlapLookupAnnotator.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.

-->
<taeDescription xmlns="http://uima.apache.org/resourceSpecifier">
   <frameworkImplementation>org.apache.uima.java</frameworkImplementation>
   <primitive>true</primitive>
   <annotatorImplementationName>org.apache.ctakes.dictionary.lookup2.ae.OverlapJCasTermAnnotator</annotatorImplementationName>
   <analysisEngineMetaData>
      <name>UmlsOverlapLookupAnnotator</name>
      <description>Lookup Annotator descriptor for Snomed Terms which are in a Rare Word -format Database, Ctakes
         and uses overlap spans for matching in addition to exact spans
      </description>
      <version/>
      <vendor/>

      <configurationParameters>
         <!-- windowAnnotations and exclusionTags were originally for the LookupConsumer, but now apply to the annotator -->
         <configurationParameter>
            <name>windowAnnotations</name>
            <description>Type of window to use for lookup</description>
            <type>String</type>
            <multiValued>false</multiValued>
            <mandatory>true</mandatory>
         </configurationParameter>
         <configurationParameter>
            <name>exclusionTags</name>
            <description>Parts of speech to ignore when considering lookup tokens</description>
            <type>String</type>
            <multiValued>false</multiValued>
            <mandatory>false</mandatory>
         </configurationParameter>
         <configurationParameter>
            <name>minimumSpan</name>
            <description>Minimum required span length of tokens to use for lookup. Default is 3</description>
            <type>String</type>
            <multiValued>false</multiValued>
            <mandatory>false</mandatory>
         </configurationParameter>
         <configurationParameter>
            <name>totalTokenSkips</name>
            <description>Specifies the number of total tokens that can be skipped. Default is 4</description>
            <type>String</type>
            <multiValued>false</multiValued>
            <mandatory>false</mandatory>
         </configurationParameter>
         <configurationParameter>
            <name>consecutiveSkips</name>
            <description>Specifies the number of consecutive non-comma tokens that can be skipped. Default is 2</description>
            <type>String</type>
            <multiValued>false</multiValued>
            <mandatory>false</mandatory>
         </configurationParameter>
         <configurationParameter>
            <name>DictionaryDescriptor</name>
            <description>Path to Dictionary spec xml</description>
            <type>String</type>
            <multiValued>false</multiValued>
            <mandatory>false</mandatory>
         </configurationParameter>            
      </configurationParameters>

      <configurationParameterSettings>
         <nameValuePair>
            <name>windowAnnotations</name>
            <value>
               <!--  LookupWindowAnnotation is supposed to be a refined Noun Phrase  -->
               <!--<string>org.apache.ctakes.typesystem.type.textspan.LookupWindowAnnotation</string>-->
               <!--  In some instances LookupWindowAnnotation is missing tokens and Sentence can be used -->
               <string>org.apache.ctakes.typesystem.type.textspan.Sentence</string>
            </value>
         </nameValuePair>
         <nameValuePair>
            <name>exclusionTags</name>
            <value>
               <string>VB,VBD,VBG,VBN,VBP,VBZ,CC,CD,DT,EX,IN,LS,MD,PDT,POS,PP,PP$,PRP,PRP$,RP,TO,WDT,WP,WPS,WRB</string>
            </value>
         </nameValuePair>
         <nameValuePair>
            <name>minimumSpan</name>
            <value>
               <string>3</string>
            </value>
         </nameValuePair>
         <nameValuePair>
            <name>totalTokenSkips</name>
            <value>
               <string>4</string>
            </value>
         </nameValuePair>
         <nameValuePair>
            <name>consecutiveSkips</name>
            <value>
               <string>2</string>
            </value>
         </nameValuePair>
         <nameValuePair>
            <name>DictionaryDescriptor</name>
            <value>
               <string>org/apache/ctakes/dictionary/lookup/fast/sno_rx_16ab.xml</string>
            </value>
         </nameValuePair>              
      </configurationParameterSettings>

      <typeSystemDescription>
         <imports>
         </imports>
      </typeSystemDescription>
      <typePriorities/>
      <fsIndexCollection/>
      <capabilities>
         <capability>
            <inputs>
               <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.BaseToken</type>
               <!--<type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textspan.LookupWindowAnnotation</type>-->
               <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textspan.Sentence</type>
            </inputs>
            <outputs>
               <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.IdentifiedAnnotation</type>
            </outputs>
            <languagesSupported/>
         </capability>
      </capabilities>
      <operationalProperties>
         <modifiesCas>true</modifiesCas>
         <multipleDeploymentAllowed>true</multipleDeploymentAllowed>
         <outputsNewCASes>false</outputsNewCASes>
      </operationalProperties>
   </analysisEngineMetaData>
</taeDescription>