USC Researchers Present 30 Papers at EMNLP 2021

| November 17, 2021 

Goals include building fairer commonsense models by reducing bias, detecting polarizing topics to mitigate conflict, and achieving smooth human-AI communication.

Image

USC researchers presented 30 papers at the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021, a tier-1 venue for researchers around the world to publish results and push the boundaries of natural language understanding and artificial intelligence.

USC papers covered a range of topics including commonsense, the field of AI that aims to help computers understand and interact with humans more naturally; continual learning, which enables models to learn and gain knowledge over time; and question answering using synthetic adversarial data generation to increase robustness.

USC Papers Presented:

Published on November 17th, 2021

Last updated on May 16th, 2024

Share this Story