PyData Triangle March 2021 Meetup

PyData Triangle welcomes you to another exciting event.

This will be an online event. You must RSVP to this meetup event in order to see the Zoom URL. If prompted, the password is 841957

Speakers:

• Rachael Tatman
• Alex Lew
• YOU: Lightning Talks (Sign-up for a 5 minute lightning talk slot at the meeting by posting in the chat. Or pre-sign-up by posting a comment into this announcement.)

Schedule:
6:00-6:15 announcements
6:15-7:00 Rachael Tatman
7:00-8:00 Alex Lew
8:00-8:30 Lightning talks

The PyData code of conduct ( http://pydata.org/code-of-conduct.html ) is enforced at this Meetup. Attendees violating these rules may be asked to leave the meetup at the sole discretion of the meetup organizer.

NOTE: This meeting will be recorded.

Please propose a presentation or speaker for a future PyData Triangle meetup. Contact any of the organizers, Gene Ferruzza, or Mark Hutchinson through meetup messages.

Follow us on twitter at: https://twitter.com/pydatatriangle

Presenter: Rachael Tatman

Title: Rules + Deep Learning: Why you need both to build Conversational AI that actually works

Presentation Overview:
Current NLP research is focused on large, neural models and these models have seen a lot of success across many different applications. But to build a conversational AI system that works well in practice, there's no getting around it: you need some rules as well. This talk with put both rules and transformer models into their historical context in NLP and discuss best practices and examples for combining them in hybrid systems.

Bio:
Rachael is a developer advocate for Rasa, where she's helping developers build and deploy conversational AI applications using their open source framework. 🤖💬

Rachael has a PhD in Linguistics from the University of Washington. Her research was on computational sociolinguistics, or how our social identity affects the way we use language in computational contexts. Previously she was a data scientist at Kaggle and is still a Grandmaster.

Presenter: Alex Lew

Title: Probabilistic Scripting for Common-Sense Data Cleaning at Scale

Presentation Overview:
Real-world data is often messy and incomplete, littered with typos, duplicates, NULL values, and other errors or inconsistencies. Although cleaning dirty data is important for many workflows, it has proven difficult to automate: cleaning often requires common-sense reasoning and judgment calls about objects in the world.

In this talk, I’ll introduce a new declarative-programming approach to automating common-sense data cleaning, based on recent advances in probabilistic programming. Our system, PClean, allows users to declare their uncertain knowledge about their datasets declaratively, and compiles efficient cleaning algorithms guided by the scripts. We’ll look at the probabilistic programming ideas that make PClean tick, and show how short (< 50-line) scripts can achieve state-of-the-art accuracy and performance on several cleaning tasks, scaling to millions of rows.

Bio:
Alex Lew is a Ph.D. student at MIT's Probabilistic Computing Project, and a lead researcher for Metaprob, an open-source probabilistic programming language embedded in Clojure(Script). He aims to build tools that empower everyone to use probabilistic modeling and inference to solve problems creatively. Before coming to MIT, Alex designed and taught a four-year high-school computer science curriculum at the Commonwealth School in Boston. And before that, I was a student at Yale, where I received a B.S. in computer science and mathematics in 2015. A native of Durham, NC, he also returns home each summer to teach at the Duke Machine Learning Summer School (and spend time with his family and their dogs!).