FlowQA: Grasping Flow in History for Conversational Machine Comprehension

Abstract

Conversational machine comprehension requires the understanding of the conversation history, such as previous question/answer pairs, the document context, and the current question. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations generated during the process of answering previous questions, through an alternating parallel processing structure. Compared to approaches that concatenate previous questions/answers as input, Flow integrates the latent semantics of the conversation history more deeply. Our model, FlowQA, shows superior performance on two recently proposed conversational challenges (+7.2% F1 on CoQA and +4.0% on QuAC). The effectiveness of Flow also shows in other tasks. By reducing sequential instruction understanding to conversational machine comprehension, FlowQA outperforms the best models on all three domains in SCONE, with +1.8% to +4.4% improvement in accuracy.

arXiv comment15 pages, Published at ICLR 2019

Cited by in corpus (20)

• Open-Retrieval Conversational Question Answering
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• Interactive Question Answering Systems: Literature Review
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
• Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
• A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering
• A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
• Conversational Question Answering: A Survey
• ChainCQG: Flow-Aware Conversational Question Generation
• A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension
• Weakly-Supervised Open-Retrieval Conversational Question Answering
• Advances in Multi-turn Dialogue Comprehension: A Survey
• Structural Pre-training for Dialogue Comprehension
• An Empirical Study of Content Understanding in Conversational Question Answering
• RoR: Read-over-Read for Long Document Machine Reading Comprehension
• Do not let the history haunt you -- Mitigating Compounding Errors in Conversational Question Answering
• NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
• Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering
• Self-supervised Dialogue Learning for Spoken Conversational Question Answering