Natural Language Processing for Facebook Messenger
September 15, 2017
In its continuing effort to evolve from a basic networking site to a platform for services, Facebook is making Messenger smarter. Silicon reports, “Facebook Bakes Natural Language Processing Messenger Platform 2.1.” The inclusion allows developers to create more functionality for organizations that wish to conduct chatbot-based business through Facebook Messenger itself, without having to utilize another site or app. Reporter Roland Moore-Colyer quotes Facebook’s Vivien Tong as he writes:
‘This first version can detect the following entities [within users’ messages]: hello, bye, thanks, date & time, location, amount of money, phone number, email and a URL. This is the first step in bringing NLP capabilities to all developers, enabling brands to scale their experiences on Messenger.’
The natural language processing capabilities come courtesy of Wit.aim a company Facebook acquired backing in 2015; its services have been available to developers for some time, but were not made native to the Messenger Platform until its latest iteration. Alongside in-built natural language processing, the overhauled Messenger Platform contains software development kits for developers to easily integrate payment services into Messenger and make it easier for to switch customer conversations from automated chatbots to human customer services.
Ah, yes, payment services are crucial, and being able to reach a real person is a sanity-saver (and a client-keeper.) Moore-Colyer notes this development is one in a series of advances for Messenger, and that Facebook’s embrace of smart tech extends to fighting terrorism within its platform.
Cynthia Murrell, September 15, 2017
Comments
One Response to “Natural Language Processing for Facebook Messenger”
-
- Subscribe to Beyond Search
Feature archive
News archive
-
Natural Language Processing (NLP) allows you to understand and extract meaningful information (called entities) out of the messages people send. You can then use these entities to identify intent, automate some of your replies, route the conversation to a human via livechat, and collect audience data.
If you are currently leveraging an NLP API, you have to make an extra call when you receive the user message, which adds latency and complexity (example: async, troubleshooting, etc.). With built-in NLP, entities are automatically detected in every text message that someone sends.