Technical report on Conversational Question Answering
This work addresses conversational question answering for AI systems, representing an incremental improvement with a specific performance gain.
The authors tackled conversational question answering by proposing a system combining RoBERTa with rationale tagging, adversarial training, knowledge distillation, and linguistic post-processing, achieving 90.4 F1 on the CoQA test set and outperforming the previous state-of-the-art single model by 2.6% F1.
Conversational Question Answering is a challenging task since it requires understanding of conversational history. In this project, we propose a new system RoBERTa + AT +KD, which involves rationale tagging multi-task, adversarial training, knowledge distillation and a linguistic post-process strategy. Our single model achieves 90.4(F1) on the CoQA test set without data augmentation, outperforming the current state-of-the-art single model by 2.6% F1.