Artificial Intelligence

Reasoning about objects, their components, and their descriptors

Friday, August 10, 2018, 3:00pm - 4:00pm PDTiCal
6th Floor Conf Rm- #689
This event is open to the public.
NL Seminar
James Mullenbach (USC/ISI)

Abstract: How do adjectives project from a noun to its parts and other aspects? If a motorcycle is red, are its wheels red? Is a sharp knife’s handle sharp? Questions like this are common sense for humans, using our understanding of the world, but difficult for computers. I will describe our process for curating and annotating a large dataset consisting of related object pairs and adjectives, and a set of experiments that aim to discover the extent to which modern approaches can learn these relationships from purely textual sources.

Bio: James is a Master’s Student in Computer Science at the Georgia Institute of Technology, where he works on machine learning for healthcare using written electronic health record notes. At ISI, he is working with Jonathan May and Nanyun Peng on building a dataset and models for textual commonsense reasoning. He aims to work on NLP and ML in industry for a year or so before applying for PhD programs.

« Return to Events