PiterPy 2019

Building NLP pipelines for Language Learning Chatbots

This talk focuses in the implementation of state of the art Deep Learning techniques in sequences in order to teach a model how to understand and generate language in Czech, I showcase how open source tools plus fine tuning leveraging Python can create an agent that serves as a training partner in order to learn a language, such as Czech. The building of this solution came after relocating to Prague (I am from Colombia) and finding out that typical language courses fail to address the real life natural language that is created when you interact with locals. In addition, I work as a consultant implementing Chatbots using Microsoft LUIS, and I could see how using my approach can offer a solution for countries where Microsoft cognitive services still do not support the language (such as Czech)

William Galindez Arias​
Prague, Czech
Senior Consultant
devoteam

Born and raised in Colombia, studied Electronic Engineering and specialized in Digital Electronics, former exchange student in Czech Technical University in the faculty of Data Science. I started my career working in Intel as Field Engineer, then moved to Oracle in Bogota. After 5 years in Oracle as Solution Architect I decided to get deeper in my knowledge of Machine Learning and Databases, relocated to Prague in Czech Republic, where I studied Data Science for a while from the academia perspective, later jumped to Solution Architect in CA technologies and Currently I am advisor of Colombian Startup (Octesoft) and Senior consultant in French Company (Devoteam) working as Machine Learning Architect for Large Enterprise Sector with focus in NLP/AI.