Literary novels push the limits of natural language processing. While much work in NLP has been heavily optimized toward the narrow domains of news and Wikipedia, literary novels are an entirely different animal--the long, ...

Mailchimp is the world's largest marketing automation platform. Over a billion emails are sent by it every day, which raises the question: what exactly are users sending? We'll do a deep dive into the natural language ...

Labs affiliated with the Machine Learning Center at Georgia Tech (ML@GT) will have the opportunity to share their research interests, work, and unique aspects of their lab in three minutes or less to interested graduate ...

A wave of recent work has sought to understand how pretrained language models work. Such analyses have resulted in two seemingly contradictory sets of results. On one hand, work based on "probing classifiers" generally ...

Despite large advances in neural text generation in terms of fluency, existing generation techniques are prone to hallucination and often produce output that is unfaithful or irrelevant to the source text. In this talk, ...

In this three-part talk, I will present some of our recent efforts that aim to control and adapt neural models to work more effectively in target applications. The first part will focus on how to repurpose a pre-trained ...

Modern deep learning models for natural language processing (NLP) achieve state-of-the-art predictive performance but are notoriously opaque. I will discuss recent work looking to address this limitation. I will focus ...