This extension adds support for named-entity recognition services to Google Refine / OpenRefine.
![[Screenshot of the extension]](http://freeyourmetadata.org/images/ner-extension.png)
- Download the zip file from the latest release
- If it does not exist, create a folder named extensions/ner under your user workspace directory for OpenRefine. The workspace should be located in the following places depending on your operating system (see OpenRefine FAQ for more details):
- Linux ~/.local/share/OpenRefine
- Windows C:/Documents and Settings//Application Data/OpenRefine OR C:/Documents and Settings//Local Settings/Application Data/OpenRefine
- Mac OSX ~/Library/Application Support/OpenRefine
- Unzip the downloaded release into the extensions/ner folder (step 1).
- Restart OpenRefine (OpenRefine usage instructions are provided in the user documentation)
- Open or create a project
- Click the Named-entity recognition button at the top right, choose Configure services....
- Click the small triangle before the column name and choose Extract named entities...
- Select the services you want to use.
- Click Start extraction.
In order to use StanfordNLP an instance of the service must be running.
- Download the NLP service software
- Extract the download, and from within the extracted directory run
java -mx4g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer -port 9000 -timeout 15000
The Named-Entity Recognition extension has been developed as part of the Free Your Metadata initiative.
This extension is provided free of charge under the MIT license.
If this extension is used for research, we kindly ask that you refer to the associated paper in your publications:
van Hooland, S., De Wilde, M., Verborgh, R., Steiner, T., and Van de Walle, R.
Exploring Entity Recognition and Disambiguation for Cultural Heritage Collections.
Digital Scholarship in the Humanities, Vol. 30 Iss. 2, pp. 262–279, 2015.
- Execute
mvn package assembly:single - Extension will be located into
target/