Workshops by Ona de Gibert

I am a Research Engineer at the Barcelona Supercomputing Center. I graduated in Modern Languages and Literature at the University of Barcelona and hold a Master’s degree by the University of the Basque Country in Language Analysis and Processing.

Having worked as a Computational Linguist for several years, my current position is as a Language Data Engineer in the field of Machine Translation. My main areas of research include low-resourced languages, data curation and anonymization.

In my free time, I love to give workshops and spread the word about about my favourite topic: Natural Language Processing! Here you can find some of the workshops and events I have conducted.

1. Linguists are scientists too

• Targeted Audience: anyone
• Format: Talk
• Duration: 10 min
• Sample Link

Description

Short talk introducing what is Natural Language Processing for anyone interested in languages and technology. It gives an overview of the field of Natural Language Processing (NLP) and its presence in our everyday lives.

Contents

• What is NLP?
• NLP is everywhere
• A bit of history
• Use case: Unsupervised Machine Translation for low-resourced languages
• Linguists are scientists too

2. Practical Introduction to NLP and ML

• Targeted Audience: programmers not familiar with python nor nlp nor ml
• Format: Workshop
• Duration: 2h and 30 min
• Sample Link

Description

New to Python? Never heard of Natural Language Processing? Never heard of Machine Learning? In this workshop we'll learn what is NLP and we'll get familiar with ML by running our very first model for Spam detection.

Contents

• What is NLP?
• WHat are regular expressions?
• Practical Exercise!
• What is Machine Learning?
• Two algorithms: Naive Bayes and Random Forest
• Practical Exercise!

3. What is the AirBnb Scenario in Berlin? A text-based analysis of the reviews

• Targeted Audience: data scientists experiencied with pyhton, pandas and ml
• Format: Workshop
• Duration: 1h
• Sample Link

Description

In this session we'll explore the AirBnB Dataset to find out what the visitors have to say about the hospitality industry of the German capital. We will use some text preprocessing techniques to be able to build our models for two machine learning techniques: Sentiment Analysis (supervised) and Topic Modelling (unsupervised).

Contents

• What is NLP
• How do we apply the scientific method to NLP
• Practical Exercise
• Q&A