Events

Kyle Gorman (City University of New York) ” Weighted Finite-State Transducers: The Later Years”

February 28, 2022
When: April 1, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234, 3400 N. Charles Street, Baltimore, MD 21218

Abstract While the “deep learning tsunami” continues to define the state of the art in speech and language processing, finite-state transducer grammars developed by linguists and engineers are still widely used in industrial, highly-multilingual settings,[…]

Read More

Student Seminar – Sonal Joshi “Classify and Detect Adversarial Attacks Against Speaker and Speech Recognition Systems”

February 28, 2022
When: March 4, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Adversarial attacks deceive neural network systems by adding carefully crafted perturbations to benign signals. Being almost imperceptible to humans, these attacks pose a severe security threat to the state-of-the-art speech and speaker recognition systems, making[…]

Read More

Ana Marasović (Allen Institute for AI & University of Washington) “Self-Explaining for Intuitive Interaction with AI”

February 18, 2022
When: February 28, 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 Since it is increasingly harder to opt out from interacting with AI technology, people demand that AI is capable of maintaining contracts such that it supports agency and oversight of people who are required[…]

Read More

Hanna Hajishirzi (University of Washington & Allen Institute for AI ) “Toward Robust, Knowledge-Rich NLP”

February 18, 2022
When: February 25, 2022 @ 12:00 pm – 1:15 pm
Where: Ames Hall 234 – Presented Virtually Via Zoom https://wse.zoom.us/j/96735183473

Abstract Enormous amounts of ever-changing  knowledge are available online in diverse textual styles and diverse formats. Recent advances in deep learning algorithms and large-scale datasets are spurring progress in many Natural Language Processing (NLP) tasks,[…]

Read More

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

Center for Language and Speech Processing