Seminars

Sep
30
Fri
Antonios Anastasopoulos (George Mason University) “NLP Beyond the Top-100 Languages” @ Hackerman Hall B17
Sep 30 @ 12:00 pm – 1:15 pm

Abstract

The availability of large multilingual pre-trained language models has opened up exciting pathways for developing NLP technologies for languages with scarce resources. In this talk I will advocate for the need to go beyond the most common languages in multilingual evaluation, and on the challenges of handling new, unseen-during-training languages and varieties. I will also share some of my experiences with working with indigenous and other endangered language communities and activists.

Biography

Antonios Anastasopoulos is an Assistant Professor in Computer Science at George Mason University. In 2019, Antonis received his PhD in Computer Science from the University of Notre Dame and then worked as a postdoctoral researcher at the Language Technologies Institute at Carnegie Mellon University. His research interests revolve around computational linguistics and natural language processing with a focus on low-resource settings, endangered languages, and cross-lingual learning.

 

Oct
3
Mon
Student Seminar @ Hackerman Hall B17
Oct 3 @ 12:00 pm – 1:15 pm
Oct
7
Fri
Ariya Rastrow (Amazon) @ Hackerman Hall B17
Oct 7 @ 12:00 pm – 1:15 pm
Oct
14
Fri
He He (New York University) “What We Talk about When We Talk about Spurious Correlations in NLP” @ Hackerman Hall B17
Oct 14 @ 12:00 pm – 1:15 pm

Abstract

Model robustness and spurious correlations have received increasing attention in the NLP community, both in methods and evaluation. The term “spurious correlation” is overloaded though and can refer to any undesirable shortcuts learned by the model, as judged by domain experts.

When designing mitigation algorithms, we often (implicitly) assume that a spurious feature is irrelevant for prediction. However, many features in NLP (e.g. word overlap and negation) are not spurious in the sense that the background is spurious for classifying objects in an image. In contrast, they carry important information that’s needed to make predictions by humans. In this talk, we argue that it is more productive to characterize features in terms of their necessity and sufficiency for prediction. We then discuss the implications of this categorization in representation, learning, and evaluation.

Biography

He He is an Assistant Professor in the Department of Computer Science and the Center for Data Science at New York University. She obtained her PhD in Computer Science at the University of Maryland, College Park. Before joining NYU, she spent a year at AWS AI and was a post-doc at Stanford University before that. She is interested in building robust and trustworthy NLP systems in human-centered settings. Her recent research focus includes robust language understanding, collaborative text generation, and understanding capabilities and issues of large language models.

Oct
17
Mon
David Chiang (University of Notre Dame) @ Hackerman Hall B17
Oct 17 @ 12:00 pm – 1:15 pm
Oct
24
Mon
Fei Sha (University of Southern California) @ Hackerman Hall B17
Oct 24 @ 12:00 pm – 1:15 pm
Nov
4
Fri
Berrak Sisman (University of Texas at Dallas) @ Hackerman Hall B17
Nov 4 @ 12:00 pm – 1:15 pm
Nov
11
Fri
Hui Guan (University of Massachusetts Amherst) @ Hackerman Hall B17
Nov 11 @ 12:00 pm – 1:15 pm
Nov
18
Fri
Angela Fan (Facebook) @ Hackerman Hall B17
Nov 18 @ 12:00 pm – 1:15 pm
Dec
2
Fri
Minje Kim (Indiana University) @ Hackerman Hall B17
Dec 2 @ 12:00 pm – 1:15 pm

Center for Language and Speech Processing