After clicking “Watch Now” you will be prompted to login or join.
Click “Watch Now” to login or join the NVIDIA Developer Program.
Modularizing Natural Language Processing
Zhengzhong Liu, Carnegie Mellon University | Zecong Hu, Carnegie Mellon University
Recent success and growth in natural language processing and artificial intelligence have given the world many new applications, techniques, models, and architectures. We'll show how appropriate abstraction and modularization can streamline both development and deployment of NLP technologies. We'll provide a systematic overview of NLP abstractions and breakdown, the insights of machine learning integration, and the designs of NLP systems for fast module development. You'll learn to use off-the-shelf tools to practice the modularized NLP and build practical applications. Our talk is suitable for researchers and practitioners with an intermediate-level understanding of NLP and ML concepts and applications, and a strong interest in real-world NLP application design and development.