Papers by Shuwen Deng
Pre-Trained Language Models Augmented with Synthetic Scanpaths for Natural Language Understanding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for augmenting language models with human scanpaths have been developed, but the potential of synthetic gaze data across NLP tasks remains unexplored. |
| Approach: | They propose to combine synthetic scanpath generation with a scanpath-augmented language model, eliminating the need for human gaze data. |
| Outcome: | The proposed model outperforms the underlying language model and achieves comparable performance to a language model augmented with real human gaze data. |
Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing corpora of eye-tracking-while-reading corporata lack diversity, limiting their ability to include primarily native speakers. |
| Approach: | They expand the eye-tracking-while-reading dataset CopCo by incorporating a new dataset of L2 readers with diverse L1 backgrounds. |
| Outcome: | The extended CopCo corpus comprises neurotypical L1 and L1 readers with dyslexia as well as L2 readers reading the same materials. |
Fine-Tuning Pre-Trained Language Models with Gaze Supervision (2024.acl-short)
Copied to clipboard
| Challenge: | Existing pre-trained language models lack a gaze module to exploit cognitive signals. |
| Approach: | They propose to integrate a gaze module into pre-trained language models at the fine-tuning stage to exploit cognitive signals. |
| Outcome: | The proposed model improves performance on the GLUE benchmark and standard fine-tuning and text augmentation baselines. |