[Online Talks] An Evening with BERT - language modelling and processing

![[Online Talks] An Evening with BERT - language modelling and processing](https://secure.meetupstatic.com/photos/event/b/a/1/4/highres_490187636.webp?w=750)
Details
Let’s learn all about BERT-ology from two female experts who will talk about Google’s natural language processing model at our next virtual event.
BERT (Bidirectional Encoder Representations from Transformers) is a popular, state-of-the-art language model that is used in a wide variety of NLP tasks, including question answering, chatbots, natural language inference and others.
---
#1: "Non coding Super power! – Algorithms for your everyday life"
by Heike Quosdorf
#2: "Intro to BERT-ology, covering some of the investigations into how BERT works"
by Rachael Tatman
#3: "How Does BERT Answer Questions? - A Look Inside Current Deep Learning Models for NLP"
by Betty van Aken
• Description: Current state-of-the-art models in NLP are Deep Neural Networks like “BERT” that draw decisions based on learned representations of text. While their results are often surprisingly good, we have little understanding of what is happening inside the Neural layers and how this affects the predictions. In this talk, we try to take a look inside the inner states of a model that is trained on Question Answering to gain a better understanding of its internal process and to identify potential shortcomings.
• Speaker:
About Rachel:
Rachel is a Senior Developer Advocate at Rasa Technologies Inc. in Seattle, where she is helping devlopers build and deploy conversational AI applications with RASA’s open source framework. With a PhD in Linguistics her research was on computational sociolinguistics, or how our social identity affects the way we use language in computational contexts. Rachael is also one of the organizers of R-Ladies Seattle.
About Betty:
Betty works as a researcher and PhD student at Beuth University of Applied Sciences in Berlin. She currently focuses on NLP applications for the medical domain. She also loves to develop small chatbots in her spare time.
About Heike:
Heike is a self/community taught Python developer and career changer. After working for several years in the film industry as colourist and technical operator she is now developing image processing and analysis tools with Python.
• Audience level:
Basic understanding of Python, in addition some basic knowledge of AI and ML will help you while we explore the topic, but is not required.
• Schedule
19:00h – Community introduction
19:10h – Non coding Super power!
19:20h – Talk #1: Intro to BERT-ology
19:40h – Q&A
19:45h – short BREAK
19:50h – Talk #2. How Does BERT Answer Questions?“
20:10h – Q&A
20:15h – See you next time \o/
---
This event will be broadcast on Twitch. Please RSVP by clicking the "Attend Online" button to access the link.
• Gender policy
We believe knowledge is for all and at the same time, our events aim primarily to empower women tech community. We request non-female attendees to be aware of this situation and make their presence discreet. Eg. by inviting women to attend, avoiding dominating the discussions or Q&A. By attending our online event, you agree to the PyLadies Code of Conduct: https://www.pyladies.com/CodeOfConduct/
• Photography / Video Consent
We take photos and videos during the event to use for documentation and in social media such as here in Photo albums, Facebook, Twitter, etc. By joining the meetup, you willingly give consent to take photos and videos of you. If you do not want to give your consent, please let us know at check-in.
• Contact
Interested in speaking at one of our events? Have a good idea for a Meetup? Get in touch with us at berlin@pyladies.com
You can also find us on the PyLadies Global workspace:
- Go to https://slackin.pyladies.com and enter your email address. You should immediately receive an email invitation.
- Once you accept the invitation, go to workspace https://pyladies.slack.com
- Join channel #city-berlin and #germany

Sponsoren
[Online Talks] An Evening with BERT - language modelling and processing