Search Results for author:
Found 11 papers, 8 papers with code
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
We introduce a benchmark to measure the time to pre-train models on given GPUs and also identify ideal settings for maximizing training speed.
Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
The meta-templates for a dataset produce training examples where the input is the unannotated text and the task attribute and the output consists of the instruction and the response.
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
Large-scale neural network models combining text and images have made incredible progress in recent years.
CEREAL: Few-Sample Clustering Evaluation
We adapt existing approaches from the few-sample model evaluation literature to actively sub-sample, with a learned surrogate model, the most informative data points for annotation to estimate the evaluation metric.
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
We perform additional experiments to show that CSP improves generalization to higher-order attribute-attribute-object compositions (e. g., old white cat) and combinations of pretrained attributes and fine-tuned objects.
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
PromptSource is a system for creating, sharing, and using natural language prompts.
TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many available labeled datasets for other tasks.
Zero-Shot Learning with Common Sense Knowledge Graphs
Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples.
Ranked #1 on
Generalized Zero-Shot Learning
on OntoNotes
Study on Unsupervised Statistical Machine Translation for Backtranslation
Machine Translation systems have drastically improved over the years for several language pairs.
Context Based Approach for Second Language Acquisition
Our system uses a logistic regression model to predict the likelihood of a student making a mistake while answering an exercise on Duolingo in all three language tracks - English/Spanish (en/es), Spanish/English (es/en) and French/English (fr/en).
Ranked #1 on
Language Acquisition
on SLAM 2018
