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 at a more granular level. In the above example
Berlin can be
London can be
Very domain specific could be, e.g., "I need 8 paracetamol tablets", where
- Off-the-shelf Models: Use our pre-trained production-grade models through APIs and integrate them in any application.
- Language Support: 57 languages supported
- Entity Support: 36 different entities can be extracted using our pre-trained models.
- Train with AtuoNLP (coming soon): Train your own AI models to extract entities using AutoNLP.
- Accelerate Dataset Creation with our Creator Studio (coming soon): Equipped with handy utility tools, our Creator Studio is an in-browser text editor for creating datasets.
While building chatbots it is common to use entities like
These entities help the chatbot to decide which action to perform. Entities can also be stored in slots (memory of a chatbot) for 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 NER. While in most cases pre-trained entities are sufficient, you can train your custom extractor using AutoNLP.
Some practical usecases are as follows:
- Information extraction from news articles for advanced search and recommendation
- Entity extraction from legal documents for advanced search and fact checking