We present a reality check on large language models and inspect the prom...
Searching vast troves of videos with textual descriptions is a core
mult...
We introduce Dynatask: an open source system for setting up custom NLP t...
py-irt is a Python library for fitting Bayesian Item Response Theory (IR...
Open-ended human learning and information-seeking are increasingly media...
Natural language processing systems are often downstream of unreliable
i...
Quizbowl is a scholastic trivia competition that tests human knowledge a...
Modern natural language processing systems have been touted as approachi...
Exposing the weaknesses of neural models is crucial for improving their
...