Technical report on Conversational Question Answering
arXiv:1909.10772
Abstract
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.
References in corpus (8)
- Explaining and Harnessing Adversarial Examples
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Born Again Neural Networks
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- Adversarial Training Methods for Semi-Supervised Text Classification
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
- Reading Wikipedia to Answer Open-Domain Questions
- QuAC : Question Answering in Context
Cited by in corpus (12)
- Language Models are Few-Shot Learners
- Pre-trained Models for Natural Language Processing: A Survey
- Interactive Question Answering Systems: Literature Review
- GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
- RikiNet: Reading Wikipedia Pages for Natural Question Answering
- A Survey of Document Grounded Dialogue Systems (DGDS)
- Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP
- ChainCQG: Flow-Aware Conversational Question Generation
- Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering
- CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System
- Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
- Do not let the history haunt you -- Mitigating Compounding Errors in Conversational Question Answering