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

WS’04 Summer Workshop

June 1, 2004 @ 8:00 AM – August 1, 2004 @ 5:00 PM

Research Groups

Dialectal Chinese Speech Recognition
Joint Visual-Text Modeling
Landmark Based Speech Recognition

Subscribe to the CLSP Seminars Mailing List

Upcoming Seminars

12:00 pm Yulia Tsvetkov (University of Wa... @ Hackerman Hall B17

Yulia Tsvetkov (University of Wa... @ Hackerman Hall B17

Apr 26 @ 12:00 pm – 1:15 pm

Abstract Large language models (LMs) are pretrained on diverse data sources—news, discussion forums, books, online encyclopedias. A significant portion of this data includes facts and opinions which, on one hand, celebrate democracy and diversity of[...]

Add

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

Seminar Videos

ICLR 2024
https://arxiv.org/abs/2310.00840

Abstract:
Text generation models are notoriously vulnerable to errors in the training data. With the wide-spread availability of massive amounts of web-crawled data becoming more commonplace, how can we enhance the robustness of models trained on a massive amount of noisy web-crawled text? In our work, we propose Error Norm Truncation (ENT), a robust enhancement method to the standard training objective that truncates noisy data. Compared to methods that only uses the negative log-likelihood loss to estimate data quality, our method provides a more accurate estimation by considering the distribution of non-target tokens, which is often overlooked by previous work. Through comprehensive experiments across language modeling, machine translation, and text summarization, we show that equipping text generation models with ENT improves generation quality over standard training and previous soft and hard truncation methods. Furthermore, we show that our method improves the robustness of models against two of the most detrimental types of noise in machine translation, resulting in an increase of more than 2 BLEU points over the MLE baseline when up to 50% of noise is added to the data.

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

Eric Fosler-Lussier: Speech Recognition - 2000

Lecture given as part of CS 601.471/671 NLP: Self-supervised Models:
https://self-supervised.cs.jhu.edu/sp2024/

Speaker: Tianjian Li:
https://tianjianl.github.io/

Tutorial: Efficient language models -- Tianjian Li (JHU)

Abstract: High-quality datasets are crucial for improving the capabilities and training efficiency of large language models. However, current datasets are typically prepared in an ad hoc, heuristic way. In this talk, Sang Michael Xie will present principled approaches to improving and understanding language models centered on the pre-training data distribution. First, he will describe how to improve the efficiency of training multipurpose language models by optimizing the mixture of data sources with robust optimization. Second, he will discuss an efficient importance resampling method for selecting relevant data from trillion-token-scale web datasets for training a specialized model. Finally, he will introduce a first theoretical analysis of in-context learning, a key capability of language models to learn from examples in a textual prompt, that traces the capability back to modeling coherence structure in the pre-training data.

Speaker Biography: Sang Michael Xie is a computer science PhD student at Stanford University advised by Percy Liang and Tengyu Ma. His research focuses on data-centric machine learning for language models, understanding pre-training and adaptation, and pre-training and self-training methods for robust machine learning. Xie was awarded a NDSEG Fellowship and was previously a student researcher at Google Brain. His work has been recognized as one of Scientific American‘s World-Changing Ideas, published in flagship venues such as Science, and covered by media outlets including The New York Times, The Washington Post, Reuters, BBC News, IEEE Spectrum, and The Verge.

Data-distributional Approaches for Generalizable Language Models -- Sang Michael Xie (Stanford)

UBM based Acoustic Modeling for ASR (Daniel Povey) - 2009

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