Natural Language Prediction and Chatbots

18:30 - Gathering and mingling
18:45 – Welcoming
18:50 – Lecture #1: Modeling Natural Language for Data Protection: Predicting in context (Adam Bali)
19:20 – Lecture #2: How to improve user productivity through NLP (Tzoof Avny Brosh)
19:50 – Lecture #3: Chatbots & Voicebots (Amit Bendor)
20:20 - Sayonara

1st Session: Modeling Natural Language for Data Protection: Predicting in Context Recent research breakthroughs in natural language processing, together with advances in computational power, have enabled us to build machines that can automatically extract and retrieve the most relevant pieces of information from piles of unstructured texts.

This session will outline some of the NLP tasks and approaches that were used to build and deploy an AI system that detects sensitive information in enterprise scale. In predictive language solutions - from categorizing entire documents to extracting sensitive sentences or entities - the varying context of each sample is crucial. Yet, the encoding of context in ways that machines can interpret is still possible using sufficient labeled data and deep neural networks.

2nd Session: How to improve user productivity through NLP
When you think of Artificial Intelligence, do you imagine flying cars or humanoid robots? Think again. The road to building useful, useable AI products goes through much more grounded technologies.
Like your email Inbox.
Research has shown that 28% of worker’s time in the office is dedicated to email work.
With this overwhelming amount of communication, it’s easy for important tasks and requests to get forgotten or simply buried deep in your inbox. When other people rely on you, missed tasks could be very costly.
In this lecture, we will discuss our work at Microsoft for identifying the user’s commitments and tasks.
We’ll go over the challenges in analyzing free text from different domains and platforms.
And talk about the challenges in running deep learning NLP models in production, in real time, for millions of users.

3rd Session: Chatbots & Voicebots
Chatbots & Voicebots allows us to communicate in the most natural way with machines - through conversation.
You can find bots today in many forms such as personal assistants (Google Assistant, Amazon Alexa), work/productivity bots and leisure bots.
In this lecture, we'll go through the architecture and main components in an AI-powered chatbot.
We'll also try to answer -
Are bots a revolution or overhyped?
What differentiates a "smart" bot from a "simple" bot?
Where do bots excel?

Who can join us?

This session is open for everybody that is interesting in natural language and chatbots. No prior knowledge is required. The sessions are not technical!

About AI-BLOG: www.ai-blog.co.il

AI-BLOG, the first and leading Hebrew blog on machine learning, deep learning, data science, and AI.

AI-Blog Community is about people that help each other to become more professional. It’s the place to learn and to share algorithms, methods and papers summaries between members.

About the lecturer (Adam Bali):
Adam leads the data science at NetApp Cloud Compliance team, and specializes in machine and deep learning for natural-language processing. Adam holds M.Sc. in mathematics from Bar-Ilan University.

About the lecturer (Tzoof Avny Brosh, Machine Learning Researcher, Microsoft Israel):
Tzoof is a Machine Learning Researcher at Microsoft, working on making users' life easier by adding machine learning capabilities to Office365 products.

Her research focuses on natural language processing and includes topics such as semantic understanding, summarization and reinforcement learning in NLP.

About the lecturer (Amit Bendor):
Amit is a consultant in the fields of practical AI/ML, software architecture, Backend development, and CTO at Farmster - a marketplace for smallholder farmers and buyers.
Amit is co-hosting the successful podcast "Making Software", and writes in several publications including his personal blog - amitbend.com