Center for Language and Speech Processing

Events

Anjalie Field (Carnegie Mellon University) “NLP, Ethics, and Society”

February 4, 2022
When: February 21, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234 – Presented Virtually Via Zoom https://wse.zoom.us/j/96735183473, 3400 N. Charles Street, Baltimore, MD 21218

Abstract While rapid advances in technology and data availability have greatly increased the practical usability of natural language processing (NLP) models, current failures to center people in NLP research has contributed to an ethical crisis:[…]

Read More

Daniel Khashabi (Allen Institute for Artificial Intelligence) “The Quest Toward Generality in Natural Language Understanding”

February 4, 2022
When: February 18, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234 – Presented Virtually Via Zoom https://wse.zoom.us/j/96735183473, 3400 N. Charles Street, Baltimore, MD 21218

Abstract As AI-driven language interfaces (such as chat-bots) become more integrated into our lives, they need to become more versatile and reliable in their communication with human users. How can we make progress toward building[…]

Read More

Rowan Zellers (University of Washington) ” Grounding Language by Seeing, Hearing, and Interacting”

February 4, 2022
When: February 14, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234 – Presented Virtually Via Zoom https://wse.zoom.us/j/96735183473, 3400 N. Charles Street, Baltimore, MD 21218

Abstract As humans, our understanding of language is grounded in a rich mental model about “how the world works” – that we learn through perception and interaction. We use this understanding to reason beyond what[…]

Read More

Student Seminar – Saurabhchand Bhati “Segmental Contrastive Predictive Coding for Unsupervised Acoustic Segmentation”

February 4, 2022
When: February 11, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Automatic discovery of phone or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ contrastive predictive coding (CPC), where the model learns representations by predicting the next frame[…]

Read More

Student Seminar – Keith Harrigian “The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health during the COVID-19 Pandemic”

February 3, 2022
When: February 7, 2022 @ 12:00 pm – 1:15 pm
Where: In Person or Virtual Option @ https://wse.zoom.us/j/96735183473, 234 Ames Hall, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Social media allows researchers to track societal and cultural changes over time based on language analysis tools. Many of these tools rely on statistical algorithms which need to be tuned to specific types of[…]

Read More

Mahsa Yarmohammadi (Johns Hopkins University) “Data Augmentation for Zero-shot Cross-Lingual Information Extraction”

February 1, 2022
When: February 4, 2022 @ 12:00 pm – 1:15 pm
Where: Ames 234 Presented Virtually via Zoom https://wse.zoom.us/j/96735183473

Abstract In this talk, I present a multipronged strategy for zero-shot cross-lingual Information Extraction, that is the construction of an IE model for some target language, given existing annotations exclusively in some other language. This[…]

Read More

Tom McCoy (Johns Hopkins University) “Opening the Black Box of Deep Learning: Representations, Inductive Biases, and Robustness”

January 26, 2022
When: January 31, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Natural language processing has been revolutionized by neural networks, which perform impressively well in applications such as machine translation and question answering. Despite their success, neural networks still have some substantial shortcomings: Their internal[…]

Read More

Subscribe

Subscribe to the CLSP Seminars Mailing List

Upcoming Seminars

Sep
29
Mon
12:00 pm NUTMEG: Separating Signal From N... @ Hackerman Hall B17
NUTMEG: Separating Signal From N... @ Hackerman Hall B17
Sep 29 @ 12:00 pm – 1:15 pm
Abstract: NLP models often rely on human-labeled data for training and evaluation. Many approaches crowdsource this data from a large number of annotators with varying skills, backgrounds, and motivations, resulting in conflicting annotations. These conflicts[...]
Oct
3
Fri
12:00 pm Propaganda is already influencin... @ Hackerman Hall B17
Propaganda is already influencin... @ Hackerman Hall B17
Oct 3 @ 12:00 pm – 1:15 pm
Abstract Millions of people around the world query (prompt) large language models for information. While several studies have compellingly documented the persuasive potential of these models, there is limited evidence of who or what influences[...]

Center for Language and Speech Processing