Entities play a major role in language understanding.
To perform an action on a certain user query you not only need to understand the intent behind it but also the entities present in it.
E.g., if someone says "flights from Berlin to London", the intent here is
flight-search and entities are
London, which are of type
In a given piece of text, entities can be anything from names, addresses, account numbers to very domain specific terms like names of chemicals, medicines, etc. Essentially any valuable information that can be extracted from text.
Entities can be looked at a more granular level. In the above example
Berlin can be
London can be
Another domain-specific example could be, e.g., "I need 8 paracetamol tablets", where
👉 Quickstart are getting-started instructions to guide you through building your first Entity Recognition model in under 15 minutes.
Build use-cases via tutorials
👉 Tutorials: Explore tutorials on real-world datasets for practical use-cases.
👉 Concepts: Understand all fundamental service functionality and features of Entity Recognition to build your own project.
- Off-the-shelf Models: Use our pre-trained production-ready models through APIs and CLI commands and integrate them in any application.
- Language Support: 87 languages supported.the
- Entity Basket while using pre-trained models: 36 different entities can be extracted.
- Train with AutoNLP: Using our Entity Recognition Service you can train your own AI models to extract entities.
- Integrate and Scale with AutoMLOps: Scale or replicate your deployed models for higher availability and throughput and integrate them with your software through REST APIs.
- Accelerate Dataset Creation with our Data Studio: Equipped with handy utility tools for entity marking and phonetic typing, our Data Studio is an in-browser text editor for creating entity recognition datasets.
Our Entity Recognition Service can be used in multiple scenarios across a variety of industries:
When building chatbots it is common to recognize entities like
These entities help the chatbot to decide which specific action to perform, e.g., which shoe model in what size to place in the basket of an online shop. Entities can also be stored in slots (memory of a chatbot) to perform custom actions.
Information Extraction from Documents
Information like names, places, dates, organization, or any domain-specific terminology like names of medicines, or chemical compounds can be extracted from text documents using Entity Recognition. These solutions are helpful to enhance and enrich semantic search and also build advanced recommendation systems.
While in most cases pre-trained entities are sufficient, you can train your custom extractor using AutoNLP.
Financial and Legal Enterprises
Instead of manually reviewing significantly long text files to audit and apply policies, IT departments in financial or legal enterprises can use custom Entity Recognition in multliple languages to build automated solutions. These solutions can be helpful to enforce compliance policies, ensure fact-checking and set up necessary business rules based on knowledge mining and advanced search pipelines that process structured and unstructured content.
👉 Use our Entity Recognition models out of the box.
👉 Train your own Entity Recognition models using NeuralSpace AutoNLP: Click, Train and Deploy!
👉 Check out our language support
👉 Review the glossary to learn more about concepts and terms used throughout the documentation for our Entity Recognition Service.