Joel Grus is a research engineer at the Allen Institute for Artificial Intelligence and the author of the bestselling O’Reilly book Data Science from Scratch: First Principles with Python. Previously he was a software engineer at Google and a data scientist at a variety of startups. He lives in Seattle, where he organizes various Data Science Happy Hours.
This talk walks us through the works of Allen Institute for Artificial Intelligence and tells us about some of its projects. The main focus was on an AI based question answering system named Aristo and it's open source version Aristo-mini which utilizes various NLP and deep learning approach to answering science questions. In the talk, the presenter talks about the corpus being used to train and various sample Python codes used to build the system using NLP and Deep Learning approach.
- The mission and projects of the Allen Institute for Artificial Intelligence
- Question answering with Aristo-mini with different solver solutions and code samples
01:30 - 07:21About Allen Institute
07:22 - 11:40 Aristo-mini
- Open source
- Why Aristo-Mini
- Evaluation service
- Data - million science question
- Corpus filtering
- Solver based class - Python implementation
11:41 - 28:44 How do I answer a question?