Wit.ai at F8 2019

Recap

Thank you to everyone who made it to our booth this year! Meeting many of you in person, and…

Introducing Language Identification!

Today, we’re excited to launch a new API: GET /language! This endpoint returns the n-best…

Hello speech, we love you too.

Improvements to our speech recognition technology.

As voice interactions are becoming more prevalent, we know that speech is important to you. Speech has been essential to our mission since our early beginnings, and…

New: extract song, album, tv show and movie names

What’s the status of Wit.ai’s systems?

Launching status page with reliability metrics

As part of our efforts to increase the visibility developers have into their app and its performance, we are introducing a new status page. This page displays…

All your app samples at a glance

Today, we’re excited to introduce the new Samples tab in your app to help developers manage samples…

Introducing GET /apps/:id

A way to know more about your Wit.ai app

As part of our move to make Wit easier to use programmatically, we are releasing a new API endpoint today.
 
 The engineering team has been working on rewriting the machine learning training…

Introducing GET /samples!

We are happy to announce a new API endpoint that allows you to programmatically retrieve your validated data (aka samples) directly from the Wit API. Instead of having to dig through your Wit console or having to store the validated samples yourself, you can now access them by…

A smarter wit/location

We’re introducing a smarter wit/location starting with English apps this week. This entity can now provide more information on the captured location like timezone, locality, region or country.

API updates!

Introducing DELETE /roles and DELETE /samples

We are happy to announce two new features that allow you to delete roles and samples directly from the Wit API: DELETE /roles and DELETE /samples!

Deleting roles

⭐️ New: Sentiment Analysis Entity ⭐️

Today, we are adding the built-in wit/sentiment entity to help you analyze the general sentiment of messages you receive, and identify whether a given sentence is positive, neutral or negative. This is an effective way to gauge the overall sentiment of people using…

We are now over 160K Wit hackers!

When we joined Facebook 3 years ago, our community counted 5,000 developers. Today, we are excited…

Wit.ai at F8

Recap

Thanks to everyone who stopped by our booth! It’s was nice to meet you and see all the great…

🚀Built-in NLP Integration with Page Inbox 🚀

Last year we launched built-in NLP to enable developers to easily integrate NLP in their Messenger bot. When built-in NLP is enabled, it automatically extracts relevant information as entities in the messages your bot receives. Today we support 14…

Welcome to the (new) Wit.ai blog

Welcome to the new home of our blog — we’re excited you’re here! For those of you who aren’t familiar with the Wit.ai blog, this is where we keep our developer community up to speed on the latest from our team, and help folks make the most out of Wit.ai. We’ll use this…

Community Update — February 2018

We are grateful to our community who continues to give us feedback and help inform our roadmap for Wit. Your input on our issue tracker and FB dev group has a direct impact on what we build and improve. Today we are excited to share our plans for the rest of 2018, and…

Toward smarter entities

First of all, Happy New Year from the Wit team!

Today, we’re adding the wit/notable_person entity to help you detect and get information on notable people. Previously, you had to create a custom entity, provide a lot of training data, and find the corresponding…

Proactive annotations

As part of our ongoing efforts to make Wit.ai easier and more pleasant to use, we are launching a new version of our sentence annotation widget in the web console.

When you type a new sentence in the Understanding tab to teach a new app or improve an existing one…

Messenger Built-In NLP

We are excited to announce 3 updates to Built-In NLP. A few months ago, we released Built-in NLP with the Messenger Platform 2.1 to make it easier for developers to leverage the Wit NLP API when building for Messenger. Built-In NLP allows developers to get default entities (thanks, bye…

Locale support for dates and times

Today, we are adding locale support to improve detection and resolving of date and time expressions.

Context is key in NLP. This is especially true when trying to understand dates or locations. For instance, “today” will be interpreted as…

Clearer controls over entity lookup strategies

Today we are making it easier for you to know how Wit finds entities in a sentence. Wit allows you to extract meaning from a user query as a list of entities. We employ various lookup strategies for entities, as described in our docs. Wit can use…

Introducing Insights, a way to better understand your app performance

Today, we’re releasing Insights to help you better understand and iterate upon the performance of your Wit app. As a first step we are launching a tool within Insights that makes it easier to set the confidence…

Launching Built-in NLP for Messenger and Sunsetting Bot Engine (beta)

We have a few updates to share with you today — most exciting is the launch of Built-in NLP for Messenger, launching with Messenger Platform 2.1 just released today.

Open Sourcing our new Duckling

Wit relies both on machine learning and rules-based systems. One of these rule-based systems is Duckling, our open-sourced probabilistic parser to detect entities like dates and times, numbers, and durations. Due to our extensive growth, Duckling was not scaling as fast as…