shingle-topic-model.conf.schema.xml Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of org.apache.stanbol.enhancer.engine.topic Show documentation
Implementation of an annotation engine that links the content item to a set of possible categories from a dedicated Solr index using MoreLikeThis queries. The classification can be either applied to a complete document (text in a given language) which is the default behavior or to a specific portion of the text (using a TextAnnotation).
The newest version!
<?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. -->
<schema name="shingle-topic-model" version="1.3">
  <types>
    <fieldType name="uuid" class="solr.UUIDField" indexed="true" />

    <fieldType name="string" class="solr.StrField"
      sortMissingLast="true" omitNorms="true" />

    <fieldType name="tint" class="solr.TrieIntField"
      precisionStep="0" omitNorms="true" positionIncrementGap="0" />

    <fieldType name="tfloat" class="solr.TrieFloatField"
      precisionStep="0" omitNorms="true" positionIncrementGap="0" />

    <fieldType name="tdate" class="solr.TrieDateField"
      omitNorms="true" precisionStep="6" positionIncrementGap="0" />

    <fieldType name="random" class="solr.RandomSortField"
      indexed="true" />

    <fieldType name="text" class="solr.TextField">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory" />
        <!-- <filter class="solr.StopFilterFactory" ignoreCase="true" -->
        <!-- words="stopwords_en.txt" enablePositionIncrements="false" /> -->
        <filter class="solr.LowerCaseFilterFactory" />
        <!-- Shingle help improve the quality but they increase 
          the size of the index -->
          <filter class="solr.ShingleFilterFactory" maxShingleSize="2" outputUnigrams="true"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory" />
        <!-- <filter class="solr.StopFilterFactory" ignoreCase="true" -->
        <!-- words="stopwords_en.txt" enablePositionIncrements="false" /> -->
        <!-- <filter class="solr.SynonymFilterFactory" -->
        <!-- synonyms="synonyms.txt" ignoreCase="true" expand="true"/> -->
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.ShingleFilterFactory" maxShingleSize="2" 
          outputUnigrams="false" outputUnigramIfNoNgram="true"/>
      </analyzer>
    </fieldType>

  </types>

  <fields>
    <!-- Physical (automated) primary key. Each topic is stored into 2 Solr 
      entries to be able to handle the partial update of stored attributes such 
      as estimation of the predictive accuracy and broader topic links while preserving 
      the previous version of the statistical model -->
    <field name="entry_id" type="string" indexed="true" stored="true"
      required="true" />

    <!-- Mandatory field for all entries: this is the logical primary key -->
    <field name="concept" type="string" indexed="true" stored="true"
      required="true" />

    <!-- If entry_type can be model 'model' or 'metadata' -->
    <field name="entry_type" type="string" indexed="true" stored="true"
      required="true" />

    <!-- Mandatory classifier model attribute when entry_type == 'model' -->
    <field name="classifier_features" type="text" indexed="true"
      stored="false" termVectors="true" termPositions="false"
      termOffsets="false" />

    <!-- Classifier model stored attributes when entry_type == 'metadata' -->
    <field name="model_entry_id" type="string" indexed="true"
      stored="true" />
    <field name="primary_topic" type="string" indexed="true" stored="true" />
    <field name="broader" type="string" indexed="true" stored="true"
      multiValued="true" />
    <field name="last_update_dt" type="tdate" indexed="true"
      stored="true" />
    <!-- Accuracy evaluation of the model (accross CV folds) -->
    <field name="precision" type="tfloat" indexed="true" stored="true"
      multiValued="true" />
    <field name="recall" type="tfloat" indexed="true" stored="true"
      multiValued="true" />
    <field name="last_evaluation_dt" type="tdate" indexed="true"
      stored="true" />
    <field name="positive_support" type="tint" indexed="false"
      stored="true" multiValued="true" />
    <field name="negative_support" type="tint" indexed="false"
      stored="true" multiValued="true" />
    <!-- Store ids of some false positive and negative examples (accumulated 
      over several CV folds) -->
    <field name="false_positives" type="string" indexed="false"
      multiValued="true" stored="true" />
    <field name="false_negatives" type="string" indexed="false"
      multiValued="true" stored="true" />

  </fields>

  <uniqueKey>entry_id</uniqueKey>
  <defaultSearchField>classifier_features</defaultSearchField>
  <solrQueryParser defaultOperator="AND" />
</schema>