← Search

Yanbo Fang

2 accepted papers

2023

Rethinking Data Distillation: Do Not Overlook Calibration

ICCV 2023poster

Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods. Existing calibration methods such as temperature scaling and mixup work well for networks trained on original large-scale data. However, we find that these methods fail to cal…

Cited by 20PDFcodeScholar
2022

Data-Efficient Concept Extraction from Pre-trained Language Models for Commonsense Explanation Generation

EMNLP 2022finding

Predicting the key explanation concept is essential for generating commonsense explanations. This paper introduces a method to predict the concept from pre-trained language models for commonsense explanation generation. Our experiment found that adopting a language model as the concept extractor and…

Cited by 7SourcePDFScholar