On May 11th, we will meet for a hybrid event co-organized by ML6 and deepset! Register here on this page to join in person at the AI Campus, or register here if you want attend the Zoom meeting!
This time, we will learn about "How to Make Audio Podcasts Searchable" & "NLP for Under Represented Languages" in two talks by Nicolas Delahousse, Customer Engineer at ML6, and Sebastian Ruder, Research Scientist at Google!
On-site admission begins at 6:30pm. The talks start at 7pm. There will also be time for Q&A and small Zoom breakout rooms for online attendees to connect and discuss.
We need to count the registrations of online and in-person attendees separately. Therefore, please register here on this page if you want to join in person at the AI Campus or register here if you want attend the Zoom meeting! Looking forward to meeting you!
🎤 How to Make Audio Podcasts Searchable by Nicolas Delahousse, Customer Engineer at ML6
Podcasts have risen in popularity over the years. Despite the surge in popularity, these developments in the field of search have not been translated to the realm of podcasts until today. However, new AI models can transcribe podcasts to text and make their contents searchable. In collaboration with Checkpod, a podcast discovery website, we will demonstrate how this technology can help users find new podcasts using NLP, ElasticSearch, and Haystack.
🎤 NLP for Under-Represented Languages by Sebastian Ruder, Research Scientist at Google
Natural language processing (NLP) technology has seen tremendous improvements in recent years but most of these successes have been concentrated in languages with large amounts of data. In this talk, I will discuss challenges and potential solutions on the way to scaling NLP to more of the world’s 7000 languages. In particular, I will highlight recent progress in NLP for African languages and present methods that are applicable to languages with limited data such as employing alternative sources of data and multi-modal information.