Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering

Abstract

One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependency, and thus these models are limited in understanding human dialogues. In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ExCorD first generates self-contained questions that can be understood without the conversation history, then trains a QA model with the pairs of original and self-contained questions using a consistency-based regularizer. In our experiments, we demonstrate that ExCorD significantly improves the QA models' performance by up to 1.2 F1 on QuAC, and 5.2 F1 on CANARD, while addressing the limitations of the existing approaches.

arXiv comment12 pages, ACL 2021

References in corpus (14)

• Unsupervised Data Augmentation for Consistency Training
• Temporal Ensembling for Semi-Supervised Learning
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Adversarial Training Methods for Semi-Supervised Text Classification
• SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
• Technical report on Conversational Question Answering
• Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Semi-Supervised Sequence Modeling with Cross-View Training
• AmbigQA: Answering Ambiguous Open-domain Questions
• FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
• Logic-Guided Data Augmentation and Regularization for Consistent Question Answering
• Learning to Ask Unanswerable Questions for Machine Reading Comprehension
• A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension