Skip to main content

Key Terms

Here are some fundamental terms to build an Entity Recognition service using NeuralSpace. Click on the link to learn more!

✍️ Projects are where you can manage training examples and models for a chosen set of languages.

For example, when if are working on developing an entity extraction from news articles mechanishm in four languages, you would create a project called Entity Recognition from News Articles in the four languages you want.

✍️ Training Data (or training examples) are what our AutoNLP learns from to predict intents and entities of unseen text.

Let us take a training example, set an alarm for 25 minutes.

For entities you have to specify the start and end character index of the text you want to extract. In this case, for 25 minutes is what we are tagging as entity called datetime and the start and end index are 13 and 27 respectively.


Multiple entities can be added to the same training example.

✍️ If you would like to learn more about Entities and use the five different types supported by NeuralSpace i.e,

  • Pretrained Entities
  • Regular Expressions
  • Lookup Entities
  • Synonyms
  • Trainable Entities

✍️ Train using AutoNLP on the NeuralSpace Platform where you do not need any machine learning knowledge.

Sometimes while training a model, specifically when you have less training data, same model when trained seperately multiple times can show slight variation in performance (2-4%). To solve this, you can parallelly run multiple train jobs for the same data and then select the model which gives the best performance.

✍️ Once you have successfully trained your model which means that trainingStatus for your model is Completed, you can Deploy using AutoMLOps.

You don't have to worry about MLOps or DevOps at all.

Scaling out your models is as simple as specifying how many replicas you want and our platform will manage the deployment for you.

✍️ Parse Text where you use the parse command to access any deployed model and parse any unseen piece text that the model has not ever seen before.

✍️ Entity Recognition Metrics to learn about Strict and Partial F1 metrics used by NeuralSpace to evaluate model performance.