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

Calendar

Seminar Videos

Presenter: Karthik Narasimhan (Princeton University)

Abstract

Large language models (LLMs) have ushered in exciting capabilities in language understanding and text generation, with systems like ChatGPT holding fluent dialogs with users and being almost indistinguishable from humans. While this has obviously raised conversational systems and chatbots to a new level, it also presents exciting new opportunities for building artificial agents with improved decision making capabilities. Specifically, the ability to reason with language can allow us to build agents that can 1) execute complex action sequences to effect change in the world, 2) learn new skills by ‘reading’ in addition to ‘doing’, and 3) allow for easier personalization and control over their behavior. In this talk, I will demonstrate how we can build such language-enabled agents that exhibit the above traits across various use cases such as multi-hop question answering, web interaction, and robotic tool manipulation. In the end, I will also discuss some dangers of using these LLM-based systems and some challenges that lie ahead in ensuring their safe use.

Biography

Karthik Narasimhan is an assistant professor in the Computer Science department at Princeton University and a co-Director of the Princeton NLP group. His research spans the areas of natural language processing and reinforcement learning, with the goal of building intelligent agents that learn to operate in the world through both their own experience (”doing things”) and leveraging existing human knowledge (”reading about things”). Karthik received his PhD from MIT in 2017, and spent a year as a visiting research scientist at OpenAI contributing to the GPT language model, prior to joining Princeton in 2018. His research has been recognized by the NSF CAREER, a Google Research Scholar Award, an Amazon research award (2019), Bell Labs runner-up prize and outstanding paper awards at EMNLP (2015, 2016) and NeurIPS (2022).

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

Abstract

In this talk, I will discuss a number of projects aimed at improving HLT applications across a broad range of typologically diverse languages by modeling morphological structure. These include the creation of a very large, normalized morphological paradigm database derived from Wiktionary, consensus-based morphology transfer via cross-lingual projection, and approaches to lemmatization and morphological analysis and generation based on recurrent neural network architectures. Much of this work falls under the umbrella of the UniMorph project here at CLSP, led by David Yarowsky and supported by DARPA LORELEI, and was developed in close collaboration with John Sylak-Glassman.

Biography

Dr. Christo Kirov, PhD, is a Postdoctoral Research Fellow at the Center for Language and Speech Processing at JHU, working with David Yarowsky. His current research combines novel machine learning approaches with traditional linguistics to represent and learn morphological systems across the world’s languages, and to leverage this level of language structure in Machine Translation, Information Extraction, and other HLT tasks. Prior to joining CLSP, he was a Visiting Professor at the Georgetown University Linguistics Department. He has received his PhD in Cognitive Science from Johns Hopkins University studying under Colin Wilson, with dissertation work focusing on Bayesian approaches to phonology and phonetic expression.

Rich Morphological Modeling for Multi-lingual HLT Applications -- Christo Kirov (JHU) - 2016

NLP Research for Commercial Development of Writing Evaluation Capabilities – Jill Burstein - 2005

Abstract
In the last few years DNNs have become the dominant technique for acoustic modeling in automatic speech recognition (ASR). The diverse set of approaches proposed to further improve ASR performance includes DNN- based acoustic modeling that uses speech production knowledge (SPK), i.e., information about how the vocal tract produces speech sounds.
While standard acoustic modeling already relies on some phonological SPK binary features (e.g., fricative) to model phonetic context and define the DNN targets, more explicit uses of SPK for DNN acoustic model training can be explored.
In this talk I will be presenting two SPK-based approaches. The first approach relies on measurements of vocal tract movements to extract new acoustic features that are appended to the DNN input vector. The second approach extracts continuous valued SPK features from binary phonological features which are then used to build a structured output for the DNN. The two approaches, tested on mngu0 and TIMIT datasets, show a consistent phone recognition error reduction over a baseline that does not use SPK.
Biography

Leonardo Badino is a postdoctoral researcher at the Italian Institute of Technology (ITT), Genova, Italy. He received a M.Sc. degree in Electronic Engineering from the University of Genova in 2000 and a PhD in Computer Science from the University of Edinburgh, UK, in 2010. From 2001 to 2006 he worked as a software engineer and project manager at Loquendo, a speech technology company. During his PhD he worked on prosodic prominence detection and generation for text-to-speech synthesis. He is currently working on speech production knowledge for ASR, limited resources ASR and computational analysis of non-verbal sensorimotor communication.
https://www.iit.it/en/people/robotics-brain-and-cognitive-sciences-mirror-neurons-and-interaction-lab/post-doc/leonardo-badino.html

Speech Production Features for Deep Neural Network Acoustic Modeling -- Leonardo Badino 2015

Abstract
We describe a general approach using Bayesian analysis for the estimation of parameters in physiological pharmacokinetic models. The chief statistical difficulty in estimation with these models is that any physiological model that is even approximately realistic will have a large number of parameters, often comparable to the number of observations in a typical pharmacokinetic experiment (e.g., 28 measurements and 15 parameters for each subject). In addition, the parameters are generally poorly identified, as in the well-known ill-conditioned problem of estimating a mixture of declining exponentials Our modeling includes (a) hierarchical population modeling, which allows partial pooling of information among different experimental subjects; (b) a pharmacokinetic model including compartments for well-perfused tissues, poorly perfused tissues, fat, and the liver; and (c) informative prior distributions for population parameters, which is possible because the parameters represent real physiological variables. We discuss how to estimate the models using Bayesian posterior simulation, a method that automatically includes the uncertainty inherent in estimating such a large number of parameters. We also discuss how to check model fit and sensitivity to the prior distribution using posterior predictive simulation.

Hierarchical modeling and prior information: an example from toxicology – Andrew Gelman - 2011

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

© 2023 Johns Hopkins University

Center for Language and Speech Processing