How to automatically detect hate speech? Identify the author of a book? Search billions of web pages to give you the one you are looking for? The talk focuses on the practical side of natural language processing – from side projects to web-scale production systems. It discusses common pitfalls, shares lessons learned (the hard way) and proposes best practices. May contain bad puns.
While there is plenty of good resources available to learn the theoretical side of natural language processing, the gap between theory and practice may be a hard one to bridge. This talk focuses on the practical side by presenting several examples of using Python and deep learning for natural language processing – from tiny projects to large production systems. The author shares common mistakes, important lessons, and best practices. Whether you’re a newcomer to the field looking for tips on getting started or an experienced practitioner trying to improve your workflow, this talk will give you ideas for new projects, introduce you to modern techniques, and most importantly – let you avoid the mistakes of at least one other person.
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.