OUR SPEAKERS

speaker_badge_banner_red.png
Share on:
Asset 14icon.png
Asset 39icon.png
Asset 12icon.png

Shani is a Senior NLP Data Scientist with experience working on a variety of NLP applications in the healthcare and e-commerce industries. She researches, develops, and implements impactful AI products with a healthy sense of curiosity and creativity.

Shani holds an M.Sc. in Industrial Engineering and is the founder and manager of the NLP IL community. She is also a core team member at "Baot", Israel’s largest community of women in R&D, where she mentors fellow data scientists to pursue their next dream job.

Shani Gershtein

Senior Data Scientist
Asset 12icon.png
Asset 1TWITTER.png
Asset 39icon.png
Asset 17icon.png
linkedin.png
twitter.png
facebook.png
github.png
English, Hebrew
Languages:
Asset 7TWITTER.png
Location:
Hadera, Israel
Asset 7TWITTER.png
Can also give an online talk/webinar
Paid only. Contact speaker for pricing!

MY TALKS

Boost Your Chat-Bot Using Unsupervised Machine Translation

Data / AI / ML, Entrepreneurship

Asset 12SLIDES.png
Asset 21talk.png
Asset 11SLIDES.png

Let’s say you have a well speaking English chat-bot. You already have a successful solution for English, and you start thinking about your next users: those coming from Spain, Japan, perhaps Israel.
You’ll need to translate utterances from each language to English, run your current English flow, and - finally - translate your bot’s English response to the user’s native language.
Supervised machine translation is the obvious starting point, but getting paired corpora is very expensive, and even more so in a specific field, such as Healthcare or Finance.
In this talk, I’ll go over the steps of creating an unsupervised machine translation solution model, discuss the various challenges and opportunities, and review the latest industry solutions for understanding and generating multilingual text in specific domains, thus enhancing your bot’s language capabilities. I will also discuss the evaluation metrics and quality estimation methods you'll need to master it in production.

Asset 1icon.png

Chat-Bots Response Generation: From a Rule-Based Solution to a Full Learning Model.

Data / AI / ML

Asset 12SLIDES.png
Asset 21talk.png
Asset 11SLIDES.png

When building a chat-bot, rule-based response generation is the go-to starting point in many use cases. This is indeed a good place to start, but we can do better.
In this talk, we will survey methods for forging ahead your chat bot from a rule-based model to deep neural architectures, and the recommended steps in the middle. We'll discuss the challenges and opportunities in the space of natural language generation, how to generate text in specific domains, and how to formulate text from structured and unstructured data. We’ll also discuss evaluation metrics and quality estimation methods, to make sure you could also use your deep learning models in production.

Asset 1icon.png

The Building Blocks of Next Word Prediction

Data / AI / ML

Asset 12SLIDES.png
Asset 21talk.png
Asset 11SLIDES.png

Have you ever wondered how autocomplete works? Autocomplete sentences are currently integrated into almost every NLP tool.
In this lecture, I’ll go through the fundamentals of creating and implementing autocomplete sentences, and discuss the challenges and opportunities of achieving the desired results across domains.
In the last section, I’ll show you how to achieve exceptional results with code examples, and cover both assessment measures and quality estimation approaches. By the end of my talk, you will be able to build an accurate model for reading your users' minds.

Asset 1icon.png

Boost Your Chat-Bot Using Unsupervised Machine Translation

Completed

true

Visible

true

Order

1

Go to lecture page

Chat-Bots Response Generation: From a Rule-Based Solution to a Full Learning Model.

Completed

true

Visible

true

Order

2

Go to lecture page

The Building Blocks of Next Word Prediction

Completed

true

Visible

true

Order

3

Go to lecture page