Center for Language & Speech Processing(CLSP), JHU Courses

Multilingual Representation Distillation with Contrastive Learning

Explore multilingual sentence representations and contrastive learning for cross-lingual tasks, focusing on quality estimation of parallel sentences and low-resource languages.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Quantitative Testing with Concept Activation Vectors (TCAV) - 2018

Explore deep learning model interpretation using Concept Activation Vectors (CAVs) to quantify concept importance in classification results, with applications in image recognition and medical diagnosis.

• YouTube
• 56 minutes
• Self-Paced
• Free Video

A Synthesis of Logical Reasoning and Word Learning Abilities in Children and Adults - 2007

Explore the connection between word learning and logical reasoning in young children, challenging prevailing views on language acquisition and cognitive development.

• YouTube
• 1 hour 11 minutes
• Self-Paced
• Free Video

Multimodal Representation Learning for Vision and Language

Explore multimodal representation learning for vision and language, focusing on cross-modality decision-making and shared embedding spaces. Discover applications and challenges in this cutting-edge field.

• YouTube
• 56 minutes
• Self-Paced
• Free Video

Towards Large Language Models as Proposal Functions in a Neuro-Symbolic Expert System - 2022

Explore a reasoning system using neural language modeling for structured text-based proofs of science facts, combining classic inference engines with modern AI techniques.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Towards General-Purpose Language-Enabled Agents: Machines that can Read, Think and Act - 2023

Explore building language-enabled AI agents that can execute complex actions, learn from reading, and allow personalization. Discover applications in question answering, web interaction, and robotics.

• YouTube
• 1 hour 10 minutes
• Self-Paced
• Free Video

Rich Morphological Modeling for Multi-lingual HLT Applications - 2016

Explore advanced morphological modeling techniques for diverse languages, enhancing HLT applications through innovative approaches like neural networks and cross-lingual projection.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

NLP Research for Commercial Development of Writing Evaluation Capabilities - 2005

Explore NLP research for developing commercial writing evaluation tools, focusing on automated essay scoring and feedback systems.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

Speech Production Features for Deep Neural Network Acoustic Modeling - 2015

Explore speech production knowledge for improved DNN acoustic modeling in ASR. Learn about vocal tract measurements and phonological embeddings to enhance recognition accuracy.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Hierarchical Modeling and Prior Information in Toxicology

Explore Bayesian analysis for estimating parameters in physiological pharmacokinetic models, focusing on hierarchical population modeling and informative prior distributions for complex systems.

• YouTube
• 1 hour 20 minutes
• Self-Paced
• Free Video

Towards Web-Scale Observational Studies of Health - 2015

Explore web-scale health studies using social media analysis. Learn techniques to address confounding and selection bias, infer user attributes, and conduct observational studies beyond traditional surveillance.

• YouTube
• 56 minutes
• Self-Paced
• Free Video

Motion Magnification and Motion Denoising

Explore motion magnification and denoising techniques for video analysis and manipulation, including separating components and amplifying small movements in real-time applications.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

End-to-End Deep Learning for Broad Coverage Semantics - Semantic Role Labeling, Coreference Resolution, and Beyond

Explore end-to-end deep learning for semantic role labeling and coreference resolution, with insights on crowdsourcing large datasets for improved semantic analysis across domains.

• YouTube
• 1 hour 10 minutes
• Self-Paced
• Free Video

Under Pressure: Transforming the Way We Think About and Use Water in the Home - 2012

Explore innovative water sensing technology and visualization methods to promote efficient residential water usage and conservation through increased awareness and informed decision-making.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Target-Speaker Methods for Speech Recognition - Overlapping Speech Solutions

Explore advanced techniques for multi-talker ASR, including GPU-accelerated processing, wake-word leveraging, and self-supervised models to improve speech recognition in challenging environments.

• YouTube
• 52 minutes
• Self-Paced
• Free Video