Monday, May 4, 2020 - 11:00am to 1:00pm
For More Information, Contact:Stacey Young, email@example.com
The LTI is proud to announce the following PhD Thesis Proposal:
Learning Neural Models for Natural Language Processing in the Face of Distributional Shift
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification,span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie.that the data is sampled from a fixed distribution both at training and test time. This way of training is a far cry from how we as humans are able to learn and operate within a changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime.
The first goal of this thesis is to characterize the forms this distributional shift can take in the context of natural language processing, as well as proposed benchmarks and evaluation metrics to measure its effect on current deep learning models. We then propose methods for making neural models more robust to distributional shift.
Finally, we explore ways of efficiently adapting existing models to new domains or tasks without forgetting.
For a copy of the thesis proposal please go to the following link: