Home
About
People
Publications
Seminars
- Seminar Calendar
- Seminar Videos
Workshops
HLT Masters
Resources

Health + Safety: Coronavirus Information

July 28, 2020

Follow this link for more information from Johns Hopkins University pertaining to Coronavirus health and safety.

Categories: News

Previous Article

Subscribe

Subscribe to the CLSP Seminars Mailing List

Upcoming Seminars

There are no upcoming events.

Add

Add to Timely Calendar
Add to Google
Add to Outlook
Add to Apple Calendar
Add to other calendar
Export to XML

Seminar Videos

Abstract:
Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. While the proliferation of LLMs has enhanced numerous applications, a significant number of high-performing models remain proprietary, impeding the progress of scientific exploration. LLMs are also susceptible to hallucinations, generating seemingly credible yet factually inaccurate information that can impact their broad acceptance and integration. In this seminar, I will commence by introducing one of our open-sourced XGen LLMs. I will delve into its pre-training process and present its results on standard benchmarks. Subsequently, I will discuss our work involving reasoning with LLMs, democratizing them for low-resource languages, and distilling knowledge from a larger (175B) proprietary LLM to a smaller (7B) model in a personalized manner. Finally, I will conclude by addressing some limitations of LLMs, emphasizing that scaling alone might not suffice as a solution and that new innovations are needed to tackle these challenges.

Bio:
Dr. Shafiq Joty (https://raihanjoty.github.io/) is currently a Research Director at Salesforce Research (Palo Alto, USA), where he oversees the NLP group's efforts in large language modeling (LLM) and generative AI. He also holds the position of a tenured Associate Professor (currently on leave) in the School of Computer Science and Engineering (SCSE) at NTU, Singapore. He was a founding manager of the Salesforce Research Asia (Singapore) lab. His research has contributed to over 30+ patents and 140+ papers in top-tier NLP and ML conferences and journals. He has served as the Program Chair of SIGDIAL-2023, as a member of the best paper award committees for ICLR-23 and NAACL-22, and in the capacity of a (senior) area chair for many of the leading NLP and ML conferences.

Unleash the Potential of LLMs through Task and Data Engineering

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representations, achieving nearly lossless compression (12x) in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous speech-to-text tasks, optimizing latency, memory footprint, and quality.

Streaming Sequence Transduction through Dynamic Compression

As artificial intelligence (AI) continues to rapidly expand into existing healthcare infrastructure – e.g., clinical decision support, administrative tasks, and public health surveillance – it is perhaps more important than ever to reflect on the broader purpose of such systems. While much focus has been on the potential for this technology to improve general health outcomes, there also exists a significant, but understated, opportunity to use this technology to address health-related disparities. Accomplishing the latter depends not only on our ability to effectively identify addressable areas of systemic inequality and translate them into tasks that are machine learnable, but also our ability to measure, interpret, and counteract barriers in training data that may inhibit robustness to distribution shift upon deployment (i.e., new populations, temporal dynamics). In this talk, we will discuss progress made along both of these dimensions. We will begin by providing background on the state of AI for promoting health equity. Then, we will present results from a recent clinical phenotyping project and discuss their implication on prevailing views regarding language model robustness in clinical applications. Finally, we will showcase ongoing efforts to proactively address systemic inequality in healthcare by identifying and characterizing stigmatizing language in medical records.

Fighting Bias from Bias: Robust Natural Language Techniques to Promote Health Equity

In this presentation, we delve into the intricate world of machine learning system vulnerabilities, focusing primarily on poisoning attacks and their impact on data integrity. The speaker, research scientist Thomas Thebuad, offers a comprehensive breakdown of how data can be maliciously altered to affect machine learning outcomes, highlighting the dangers and effectiveness of both "dirty labels" and "clean label" poisoning. The talk further explores adversarial attacks, illustrating how subtle manipulations can deceive machine learning models into incorrect predictions.

This video serves as an introduction to the complex interactions between training data and system performance, emphasizing the importance of trust in data integrity. With real-world examples and theoretical insights, the speaker sheds light on various attack strategies, defense mechanisms, and the ongoing battle between system security and adversarial tactics.

Whether you're a cybersecurity expert, a machine learning enthusiast, or simply curious about the ethical implications of AI, this presentation will equip you with a deeper understanding of the challenges and necessary precautions in developing robust machine learning systems.

Adversarial and Poisoning Attacks against Speech Systems: Where to Find Them?

Abstract
The rapidity with which children acquire language is one of the mysteries of human cognition. A widely held view is that children master language by means of a language-specific learning device. An earlier proposal, generating renewed interest, is that children make use of domain-general, associative learning mechanisms in acquiring language. However, we know little about the actual learning mechanisms involved, making it difficult to determine the relative contributions of innate and acquired knowledge. A recent approach to studying this problem exposes infants to artificial languages and assesses the resulting learning. Studies using this paradigm have led to a number of exciting discoveries regarding the learning mechanisms available during infancy. This approach is useful for achieving finer-grained characterizations of infant learning mechanisms than previously imagined. Such characterizations should result in a better understanding of the relative contributions of innate and learned factors to language acquisition, as well as the dynamic between the two. I will present several studies using this methodology and will discuss the implications for the study of language acquisition.

Artificial Language Learning and Language Acquisition – Rebecca Gomez (JHU) - 2000

Load More... Subscribe

Johns Hopkins University, Whiting School of Engineering

Center for Language and Speech Processing
Hackerman 226
3400 North Charles Street, Baltimore, MD 21218-2680

(410) 516-4237
[email protected]

Whiting School of Engineering
Johns Hopkins University

Privacy Statement
Legal

© 2024 Johns Hopkins University

Center for Language and Speech Processing