Training a specialized NER model

When the data being processed is specialized, then we often need to train a model to address that specific problem domain. In this recipe, we will use OpenNLP to illustrate how this is done.

We will need to create a file that has been marked up to identify location entities. The TokenNameFinderModel class will use these markups to train a model. We will then test the model to see how well it worked.

Getting ready

To prepare, we need to do the following:

1. Create a new Maven project.
2. Add the following dependency to the POM file:

<dependency>
    <groupId>org.apache.opennlp</groupId>
    <artifactId>opennlp-tools</artifactId>
    <version>1.9.0</version&gt...