Events

Hanjie Chen (University of Virginia) “Bridging Humans and Machines: Techniques for Trustworthy NLP”

January 17, 2023

When: March 13, 2023 @ 12:00 pm – 1:15 pm

Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Advanced neural language models have grown ever larger and more complex, pushing forward the limits of language understanding and generation, while diminishing interpretability. The black-box nature of deep neural networks blocks humans from understanding[…]

CLSP Student Seminar

January 17, 2023

When: February 13, 2023 @ 12:00 pm – 1:15 pm

Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Mark Yatskar (University of Pennsylvania) “Understanding Dataset Biases: Behavioral Indicators During Annotation and Contrastive Mitigations”

January 17, 2023

When: February 10, 2023 @ 12:00 pm – 1:15 pm

Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Biases in datasets, or unintentionally introduced spurious cues, are a common source of misspecification in machine learning. Performant models trained on such data can gender stereotype or be brittle under distribution shift. In this[…]

Sharon Levy (University of California, Santa Barbara) “Responsible AI via Responsible Large Language Models”

January 17, 2023

When: February 6, 2023 @ 12:00 pm – 1:15 pm

Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract While large language models have advanced the state-of-the-art in natural language processing, these models are trained on large-scale datasets, which may include harmful information. Studies have shown that as a result, the models exhibit[…]

Sasha Rush (Cornell University) “Pretraining Without Attention”

January 17, 2023

When: February 3, 2023 @ 12:00 pm – 1:15 pm

Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Transformers are essential to pretraining. As we approach 5 years of BERT, the connection between attention as architecture and transfer learning remains key to this central thread in NLP. Other architectures such as CNNs and RNNs[…]