Grounded Natural Language Processing
Raymond J. Mooney
Time and Place
Spring 2019, Mon & Wed, 9:30-11am, GDC 2.410, (unique# 51240)
- Instructor: Mon & Wed, 11am-noon, GDC 3.512
This course will be a graduate research seminar in grounded NLP, a subarea
of AI that studies the connection between natural language and
perception and action in the world. It makes connections between NLP and
computer vision, robotics, and computer graphics. Almost all work in the
area uses machine learning to learn the connection between language and
perception and/or action from some form of multi-modal training data.
The class will mostly revolve around reading both seminal and recent research papers in the area.
Each student will be required to prepare an organized oral presentation
on one or more papers and participate in class discussion about these papers.
Many of the papers will be selected from the ones that have been covered in
the local CLAMP reading
group over the last 11 years.
Finally, it will involve conducting an original research project in the area, writing
a paper on this project suitable for submitting to a research conference,
and possibly presenting an oral presentation on the project.
The details of the specific class requirements (e.g. how many paper
presentations and whether projects are individual or group) will partly depend
on the number of students who enroll in the class.
This class is intended for graduate students actively working in NLP, computer
vision, robotics, machine learning, and/or computer graphics. Students should
have had a graduate class in at least one of these areas, ideally more than one.
A graduate NLP class such as CS 388 will be particularly valuable.