Papers by Yifu Sun
Contextual Text Denoising with Masked Language Model (D19-55)
Copied to clipboard
| Challenge: | Recent advances in NLP have been vulnerable to noisy inputs. |
| Approach: | They propose a contextual text denoising algorithm based on a ready-to-use masked language model that does not require retraining and can be integrated into any NLP system without additional training on paired cleaning training data. |
| Outcome: | The proposed algorithm can correct noise text and improve performance in several downstream tasks. |
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has shown that large language models are superior to conventional methods in various tasks. |
| Approach: | They propose a data-independent quantization algorithm that leaves outliers in the weight and quantization ranges . they find the algorithm runs over 10 times faster than the data-dependent methods . |
| Outcome: | The proposed method runs over 10 times faster than the data-dependent methods. |