What we're about
Upcoming events (5)
Topic: NLP tutorial -Part -1 ----------------------------- RSVP at https://www.eventbrite.com/e/nlp-tutorial-part-i-tickets-109888553622 Speakers Bio Fatma Tarlaci Data Science Fellow at Quansight. She specializes in Natural Language Processing (NLP) applications and data science. Prior to her current role, she was a Scholar at OpenAI where she conducted research on NLP. She has delivered (and is scheduled to deliver) technical tutorials on NLP at various conferences, including PyData Austin (2019), AnacondaCON (2020), and O’Reilly Strata Data and AI Conference (2020). She holds a Ph.D. in Comparative Literature from the University of Texas at Austin and a Master’s in Computer Science from Stanford University. Pamela Wadhwa She is Data Science Fellow at Quansight where she answers client data science requests using open-source python tools. She has 10+ years of experience developing and using scientific software for data visualization and analysis in sonar, geographical data, lidar, and neuromuscular physiology. At Quansight, she is also gaining skills in machine learning, Natural Language Processing (NLP), and data engineering. She has 2.5 years of experience teaching a biomechanics laboratory at the collegiate level. She co-taught an NLP tutorial at AnacondaCON (2020). Pamela received her Masters in Kinesiology from the University of Texas at Austin. She believes that NLP is extremely useful to effectively make sense of unstructured data that can lead to great innovations in the technological world. RSVP https://www.eventbrite.com/e/nlp-tutorial-part-i-tickets-109888553622 to get online event information. Topic: Natural Language Processing (NLP) refers to a computational understanding of human language. It constitutes a significant part of advances in AI through a variety of its applications. NLP methods are used to derive additional insights from textual and voice data, including social media that often reflects the current state of societal discourse. To demonstrate an example of how we can apply NLP methods to understand a large amount of textual data that can reveal insights into societal trends and opinions, we will use open-source NLP tools and techniques that you can use for your own learning, research and/or business interests. The tutorial will have hands-on exercises that demonstrate how to preprocess data for NLP and use sentiment analysis to reveal predominant sentiments in a set of recent tweets. Prerequisites: Python Familiarity with github Jupyter notebooks Nice-to-haves This is a beginner-friendly tutorial on NLP. Some prior knowledge of the Pandas library and a conceptual understanding of Deep Learning is nice to have, but not required.