#106 Leveraging Machine Learning and NLP for Conversational AI

<p>Today, Felipe has a few guests at the Data Science Melbourne Meet-Up Group. Former guest Prashant Natarajan and Romina Sharifpour share about their work with conversational AI. Later, Nic Ryan shares his story and tips for getting started in data science.</p> <p>Prashant starts by giving some background on the development and basics of NLP. We have made progress with deep learning and bringing machines closer to understanding human language, but it isn’t easy. Humans have a hard enough time understanding each other. What we are asking machines to do is analyze tone, find nouns, and recognize different languages. We already have things like voice to text and smart speakers, but NLP's ultimate goal is for a bot to have a conversation. True NLP is a combination of natural language understanding and language generation.</p> <p><strong>Enjoy the show!</strong></p> <p><br></p> <p><strong>We speak about:</strong></p> <ul> <li>[00:10] Introduction &amp; welcome guests<br> </li> <li>[06:45] Basics of NLP &amp; customer service<br> </li> <li>[17:45] Cleaning data and data processing<br> </li> <li>[27:30] Key takeaways from an NLP conventional AI project<br> </li> <li>[42:20] Q&amp;A with Romina and Prashant<br> </li> <li>[51:50] Meet Nic Ryan<br> </li> <li>[53:50] Nic’s start in data science<br> </li> <li>[75:00] Nic’s tips and lessons learned<br> </li> <li>[80:00] The future of machine learning<br> </li> </ul> <p><strong>Resources:</strong></p> <p><a href="https://www.meetup.com/Data-Science-Melbourne/"><u>Data Science Melbourne Meet-Up Group</u></a></p> <p><a href="https://www.linkedin.com/in/natarpr/"><u>Prashant Natarajan on LinkedIn</u></a></p> <p><a href="https://www.linkedin.com/in/rominasharifpour/?originalSubdomain=au"><u>Romina Sharifpour on LinkedIn</u></a></p> <p><a href="https://www.linkedin.com/in/nicryandataguy/"><u>Nic Ryan on LinkedIn</u></a></p> <p>Check out books from <a href="https://www.manning.com/"><u>Manning Publications</u></a>, use code <em><strong>poddatafuturology19 </strong><