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

WS’97 Summer Workshop

June 1, 1997 – August 30, 1997

Research Groups

Acoustic Processing/Modeling Group: Exploring the Time Dimension at Different Scales
Discourse LM
Pronunciation Modelling
Syllable Based Speech Processing

Click here to view the archive for the 1997 Summer Workshop.

Subscribe to the CLSP Seminars Mailing List

Upcoming Seminars

12:00 pm CLSP Student Seminar – Anna Favaro @ Hackerman Hall B17

CLSP Student Seminar – Anna Favaro @ Hackerman Hall B17

Oct 2 @ 12:00 pm – 1:15 pm

12:00 pm Antoine Bosselut (EPFL) @ Hackerman Hall B17

Antoine Bosselut (EPFL) @ Hackerman Hall B17

Oct 13 @ 12:00 pm – 1:15 pm

12:00 pm CLSP Student Seminar – Maliha Jahan

CLSP Student Seminar – Maliha Jahan

Oct 16 @ 12:00 pm – 1:15 pm

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
I will describe work on tree-based models for aligning parallel text, presenting results for models that make use of syntactic information provided for one or both languages, as well as models that infer structure directly from parallel bilingual text. In the second part of the talk, I will discuss some theoretical aspects of Synchronous Context Free Grammars as a model of translation, describing a method to factor grammars to lower the complexity of synchronous parsing.

Biography
Dan Gildea received a BA in linguistics and computer science, as well as an MS and PhD in computer science, from the University of California, Berkeley. After two years as a postdoctoral fellow at the University of Pennsylvania, he joined the University of Rochester as an assistant professor of computer science in 2003.

Syntactic Models of Alignment – Dan Gildea (University of Rochester) - 2005

Abstract:
The arms race to build increasingly larger, powerful language models (LMs) in the past year has been remarkable. Yet incorporating LMs effectively into practical applications that facilitate manual workflows remains challenging. I will discuss LMs' limiting factors and our efforts to overcome them. I will start with challenges surrounding efficient and robust LM alignment. I will share insights from our recent paper "Self-Instruct" (ACL 2023), where we used vanilla (unaligned) LMs for aligning itself, an approach that has yielded some success. Then, I will move on to the challenge of tracing the output of LMs to reliable sources, a weakness that makes them prone to hallucinations. I will discuss our recent approach of 'according-to' prompting, which steers LMs to quote directly from sources observed in its pre-training. If time permits, I will discuss our ongoing project to adapt LMs to interact with web pages. Throughout the presentation, I will highlight our progress, and end with questions about our future progress.

Bio:
Daniel Khashabi is an assistant professor in computer science at Johns Hopkins University and the Center for Language and Speech Processing (CLSP) member. He is interested in building reasoning-driven modular NLP systems that are robust, transparent, and communicative, particularly those that use natural language as the communication medium. Khashabi has published over 40 papers on natural language processing and AI in top-tier venues. His research has won the ACL 2023 Outstanding Paper Award, NAACL 2022 Best Paper Award, research gifts from the Allen Institute for AI, and an Amazon Research Award 2023. Before joining Hopkins, he was a postdoctoral fellow at the Allen Institute for AI (2019-2022) and obtained a Ph.D. from the University of Pennsylvania in 2019.

Building Helpful Language Models -- Daniel Khashabi (Johns Hopkins University)

Abstract
How are complex words stored and accessed? This answer to this question plays a crucial role in both in models of speech perception and in models of morphological productivity. Understanding the forces which lead words to be stored and accessed as wholes versus in more decomposed forms is critical for identifying the relevant domains of generalization for speech processing and for the emergence of morphological productivity.
This talk will explore ways in which frequency information is used in establishing the structure of speech signals and of words in the lexicon. It will consider both effects related to phonological pattern frequency and those related to relative lexical frequency. It will argue that experimental findings support a model in which a Fast-Phonological-Preprocessor, possibly formed in infancy, interacts with a dual-route morphological analyzer to determine both the long-term configuration of the lexicon and more implicit knowledge of phonology more generally.

Biography
Janet Pierrehumbert is Professor of Linguistics at Northwestern University. She received her Ph.D from MIT in 1980 and joined the faculty Northwestern faculty in 1989 after seven years as a Member of Technical Staff in Linguistics and Artificial Intelligence Research at AT&T Bell Laboratories. Her research interests include intonation, prosody, allophony, and lexical representation. With Mary Beckman, she coauthored the monograph Japanese Tone Structure. She co-organized the Fifth Conference in Laboratory Phonology, which took place at Northwestern in 1996. Professor Pierrehumbert has held visiting appointments at Stanford, the Royal Institute of Technology, and most recently at the CNRS in Paris as a Guggenheim fellow.

Causes and Consequences of Word Structure – Janet Pierrehumbert (Northwestern University) - 2000

Abstract
Spoken language is often conceptualized as mere sequences of words and phonemes. From this traditional perspective, the listeners task is to decode the speech signal into constituent elements derived from spectral decomposition of the acoustic signal. This presentation outlines a multi-tier theory of spoken language in which utterances are composed not only of words and phones, but also syllables, articulatory-acoustic features and most importantly prosemes, encapsulating the prosodic pattern in terms of prominence and accent. This multi-tier framework portrays pronunciation variation and the phonetic micro-structure of the utterance with far greater precision than the conventional lexico-phonetic approach, thereby providing the prospect of efficiently modeling the information-bearing elements of spoken language for automatic speech recognition and synthesis.

Biography
In the early part of his career, Steven Greenberg, studied Linguistics, first at the University of Pennsylvania (A.B.) and then at the University of California, Los Angeles (Ph.D.). He also studied Neuroscience (UCLA), Psychoacoustics (Northwestern) and Auditory Physiology (Northwestern, University of Wisconsin). He was a principal researcher in the Neurophysiology Department at the University of Wisconsin-Madison for many years, before migrating back to the “Golden West” in 1991 to assume directorship of a speech laboratory at the University of California, Berkeley, where he also held a tenure-level position in the Department of Linguistics. In 1995, Dr. Greenberg migrated a few blocks further west to join the scientific research staff at the International Computer Science Institute (affiliated with, but independent from UC-Berkeley). During the time he was at ICSI, he published many papers on the phonetic and prosodic properties of spontaneous spoken language, as well as conducted perceptual studies regarding the underlying acoustic and visual basis of speech intelligibility. He also developed, with Brian Kingsbury, the Modulation Spectrogram for robust representation of speech for automatic speech recognition as well as syllable-centric classifiers of phonetic features for speech technology applications. Since 2002, he has been President of Silicon Speech, a company based in the San Francisco Bay Area, that is dedicated to developing future-generation speech technology based on principles of human brain function and information theory. Beginning in 2004, Dr. Greenberg has also been a Visiting Professor at the Centre for Applied Hearing Research at the Technical University of Denmark where he performs speech-perception-related research.

Quest for the Essence of Language – Steven Greenberg - 2005

Abstract
Cardiac electrophysiology is a field with a rich history of integrative modeling. A particularly important milestone was the development of the first biophysically-based cell model describing interactions between voltage-gated membrane currents, pumps and exchangers, and intracellular calcium Ca2+ cycling processes in the cardiac Purkinje fiber (DiFrancesco & Noble, Phil. Trans. Roy. Soc. Lond. B 307: 353) and the subsequent elaboration of this model to describe the cardiac ventricular myocyte action potential (Noble et al. Ann. N. Y. Acad. Sci. 639: 334; Luo, C-H and Rudy, Y. Circ. Res. 74: 1071). This talk will review the “state-of-the-art”‚ in integrative modeling of the cardiac myocyte, focusing on modeling of the ventricular myocyte because of its significance to arrhythmia and heart disease. Special emphasis will be placed on the importance of modeling mechanisms of Ca2+-Induced Ca2+-Release (CICR). CICR is the process by which influx of trigger calcium (Ca2+) through L-Type Ca2+ channels (LCCs) leads to opening of ryanodine sensitive Ca2+ release channels (RyRs) in the junctional sarcoplasmic reticulum (JSR) membrane and release of Ca2+ from the JSR. It is of fundamental importance in cardiac muscle function, as it not only underlies the process of muscle contraction, but is also involved in regulation of the cardiac action potential. We will demonstrate that every model of CICR in use today has serious shortcomings, and we will offer insights as to how these shortcomings must be addressed in order to develop reconstructive and predictive models that can be used to investigate myocyte function in both health and disease. (Supported by NIH HL60133, the NIH Specialized Center of Research on Sudden Cardiac Death P50 HL52307, the Whitaker Foundation, the Falk Medical Trust, and IBM Corp)

Integrative Models of the Cardiac Ventricular Myocyte – Raimond Winslow (JHU) - 2005

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