Along with my colleagues Sarah Aerni and Jarrod Vawdrey I presented how we leverage open source tools from the Spring ecosystem to solve data science problems in NLP at scale.
You can watch a recording of this talk below.
In all industries, as software is eating the world, data is feeding software. However, to truly get value out of the data being generated, it must be analyzed and made actionable. Transformation in many industries actually means precisely this, data-driven action. From creating new television shows, to smart devices that help make your life easy, save precious limited resources, or protect your health, ingesting the data and building models are crucial to success. This session will focus on examples of how these models are built. What is required to build a model? How does data need to be processed? What do you have to consider to make your model effective? And finally what tools do I use to build these models? In this session, we will address these questions through illustrative use cases using open-source technologies varying from medical, text and sensor data, from three different speakers:
- Approaches and Open Source Tools for Wrangling and Modeling Massive Datasets
- Scaling Java Applications for NLP on MPP through PL/Java
- A Scalable Framework For Realtime Monitoring & Prediction Of Sensor Readings