Home > Unit > UMIACS

UMIACS

 

"Think before you speak": Language Generation with Planning

**Please note that the time differs from the regular meeting time**

How children are and aren’t like adults when it comes to interpreting pronouns: A developmental modeling investigation

 

Towards Human-Centered AI: Understanding Human Production and Consumption of Explanations

 

Examining Racially Biased Language within a Large Corpus American Football Commentary

 

Neural Information Retrieval: In search of meaningful progress

 

The lessons and limits of predicting shooting victimization

 

Commonsense Intelligence: Cracking the Longstanding Challenge in AI

 

Causal machine learning and challenges in decision-making with real-world data

 

Defeasible Inference in Natural Language

 

Challenges and Opportunities in Evaluating Progress in NLP

Abstract: The past few years have seen remarkable advances in NLP, as evidenced both by continued and rapid gains on benchmark tasks, as well as by the increasing prominence of real NLP systems in the wild.  In assessing such progress, however, it is important to ask not only what system achieves the best performance, but how it achieves that level of performance, how much we can trust the evaluation, and what the consequences of deploying such a system might be.

Pages

Subscribe to UMIACS