Research
Most machine reading projects have focused on macro-reading, i.e. skimming many documents to extract repeated facts or commonly expressed sentiments. I would like to focus primarily on micro-reading, which aims to extract considerable content from each individual document. I will assume that methods for natural-language processing will continue to improve, which will make micro-reading increasingly effective, and I will focus on issues like these:
- goal-directed navigation of a corpus of documents
- methods for (dis-)confirming information derived from text
- extracting information from diagrams and tables
- integrating extracted information into a knowledge base
- ways that macro-reading might inform micro-reading, and vice-versa
Publications
Component Library for building Knowledge Systems
KM knowledge representation and reasoning system
Teaching
In Spring 2019, I am teaching a new course, CS378: Practical Applications of Natural Language Processing. Here's the syllabus.
I sometimes teach CS 302: Computer Fluency. Here's the syllabus.
Contact
- O: GDC 3.704
- E: porter@cs.utexas.edu
- P: 512-471-9565