Deep Learning in Natural Language Processing has been dominated in the past years by recurrent models. But a new type of network architecture has emerged: the Transformer (Google, 2017). Unlike traditional translator models, this one does not rely on heuristics and solely focuses on attention instead of recurrence. This both reduces training time and translation quality.
As Dataiku is a growing startup with over 20 nationalities, we have decided to use this to develop our own translation bot on the company chat.
In this talk, we will explain the theory behind this model, show how to deploy it in production and give a live demo of our chatbot.
"We are impressed with the sheer volume of crowd visiting our booth. We’ve had very good interactions with the delegates and alliance partners."
Marketing Director, TIBCO Software
"We’ve met a good mix of new prospects and existing customers over the two days. There were many relevant questions posed by the delegates, attesting to the immense interest the show has generated for us leading up to the show."
Marketing – South East Asia and India, Splunk
"The conversations in the big data community around machine learning is a lot more mature here. Not only the delegates are interested in big data, they are also keen to learn more about data science, artificial intelligence and internet of things."
Regional Sales Director, Qubole Inc.
"I’m amazed with the diversity of vendors from data centre, big data, data integrators and cloud solution providers. There’s something here for almost anybody from the technology world. The most valuable takeaway for me is the opportunity to meet with our technology partners, alliance partners as well as our prospect and existing customers.!