Deep CPCFG for Information Extraction

Explore deep learning techniques for information extraction in this 41-minute lecture from MIT's Introduction to Deep Learning course. Delve into the fundamentals of information extraction, document schemas, and end-to-end deep learning philosophy. Learn about context-free grammars and their application in parsing with deep learning. Discover 2-dimensional parsing techniques and methods for handling noise in the parsing process. Examine experimental results and participate in a Q&A session. Access additional resources, including slides, lab materials, and code repositories, to further enhance your understanding of Deep Conditional Probabilistic Context Free Grammars (CPCFG) for information extraction.

​ - Introduction
- What is information extraction?
- Types of information headers, line items, etc
- Representing document schemas
- Philosophy of end-to-end deep learning
- Context free grammars CFG
- Parsing with deep learning
- Learning objective and training
- 2 dimensional parsing
- Handling noise in the parsing
- Experimental results
- Question and answering