Papers by Shanqing Cai
Context-Aware Abbreviation Expansion Using Large Language Models (2022.naacl-main)
Copied to clipboard
Shanqing Cai, Subhashini Venugopalan, Katrin Tomanek, Ajit Narayanan, Meredith Morris, Michael Brenner
| Challenge: | Existing paradigms for text entry in augmentative and alternative communication (AAC) for people with severe motor impairments require 3-5 predictions to save keystrokes. |
| Approach: | They propose a paradigm in which phrases are abbreviated aggressively as word-initial letters. |
| Outcome: | The proposed paradigm can save up to 77% on expansions on conversation turn . the proposed paradigm could be used in augmentative and alternative communication (AAC) |
Proofread: Fixes All Errors with One Tap (2024.acl-demos)
Copied to clipboard
Renjie Liu, Yanxiang Zhang, Yun Zhu, Haicheng Sun, Yuanbo Zhang, Michael Huang, Shanqing Cai, Lei Meng, Shumin Zhai
| Challenge: | Extensive experiments on a human-labeled golden set showed our tuned PaLM2-XS model achieved 85.56% good ratio. |
| Approach: | They propose a two-stage tuning approach to acquire the dedicated Large Language Model for the feature, followed by a reinforcement learning approach for targeted refinement. |
| Outcome: | The proposed model achieves 85.56% good quality on Rewrite and proofread tasks on human-labeled golden sets. |