One of the main selling points of Natural Language Processing (NLP) systems is the ability to automatically extract pieces of information from raw unstructured text. There is an entire subfield of NLP dedicated to the process of extracting and classifying bits of unstructured text into structured “entities” called Named Entity Recognition (NER).
There are all kinds of entities that people want to extract from free text. One entity that is present in almost all pieces of text are people’s names. For example, the sentence “ Matt works at Apple as an ML engineer. “ contains the person entity “Matt” as well as the organization entity “Apple”.
There are plenty of reasons why people would need to quickly extract names from free text. Chatbot designers can use name entity extraction to gather relevant user information to faster solve queries. Home automation systems use name entity extraction to automate home functions like calling or messaging someone. Name extraction technology benefits all kinds of organizations and people but up until now any kind of entity extraction system has been difficult to use.
Forefront Extract
To make name extraction as simple as an API call, we created Forefront Extract, an easy-to-use entity extraction API using state of the art AI. Using the API to extract names from text is simple and requires only two inputs:
- text — a piece of text that can be any length
- entities — A list of entity types that you are looking for. There are many entity options and the one we will highlight here is “people” — references to people by name
Let’s see the Extract API in action for the examples we outlined.
Example 1: Chatbot information gathering
Forefront Extract can parse names from a conversation to personalize a chatbot while gathering relevant information about the user to use for the future.
We can see that with Forefront Extract, a chatbot can extract and store a user’s name and use it in context while also giving that information to any future agent to help personalize the conversation.
Example 2: Home automation
A home automation system (HAS) would not be complete without the ability to talk to a friend hands-free. For example if you wanted your HAS to call a friend and ask if they want to go shopping you might say something like: “Call Becky and ask her if she wants to go to Sam’s Club”. Let’s see how Forefront Extract would handle this:
We can see that the Extract API knows to call Becky and not pull out “Sam” from Sam’s Club as a person’s name.
Get started with Forefront Extract
It’s clear from our examples that Forefront Extract can intelligently extract names and other entities from text. The possibilities unlocked by Forefront Extract are endless. Documentation for the Extract API can be found here.
Ready to sign up and get started? Sign up for Forefront today!
Originally published at https://www.forefront.ai.
