Idyl E3 Entity Extraction Engine Quick Start

This is a quick start to get you up and running with Idyl E3 Entity Extraction Engine fast and painless. To do this, we are going to launch Idyl E3 as a docker container. If you launched Idyl E3 from the AWS Marketplace you can skip installing Docker and jump down to the example commands.

First install Docker if you haven’t already. Once done, run the following commands:

docker run -p 9000:9000 -it mtnfog/idyl-e3:3.0.0

Once Idyl E3 has started, open a console and run the following command:

curl "http://localhost:9000/api/extract?language=eng" -d '["George", "Washington", "was", "president."]' -H "Content-Type: application/json"

This sends a request to Idyl E3 to extract entities from the tokenized input text. (If you need to tokenize your text take a look at Sonnet Tokenization Engine.) If you launched Idyl E3 from the AWS Marketplace you will need to substitute localhost with the public IP address of the EC2 instance. The response from Idyl E3 will look like:

{"entities":[{"text":"George Washington","confidence":0.96,"span":{"tokenStart":0,"tokenEnd":2},"type":"person","languageCode":"eng","extractionDate":1512511318007,"metadata":{"x-model-filename":"mtnfog-en-person.bin"}}],"extractionTime":2}

The NLP Building Blocks Java SDK can be used to create NLP pipelines and to integrate Idyl E3 in your existing NLP pipeline.