FlowQA: Grasping Flow in History for Conversational Machine Comprehension

TL;DR

FlowQA introduces a novel mechanism to incorporate intermediate conversation representations, significantly improving performance on conversational comprehension tasks by better understanding dialogue history.

Contribution

The paper presents Flow, a new method for integrating intermediate representations of conversation history into machine comprehension models, enhancing their ability to understand context.

Findings

+7.2% F1 on CoQA

+4.0% on QuAC

Outperforms previous models on SCONE

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.