FlowQA: Grasping Flow in History for Conversational Machine Comprehension
It addresses the problem of understanding conversation history for conversational AI, showing incremental gains over existing methods.
The paper tackles conversational machine comprehension by introducing Flow, a mechanism to incorporate intermediate representations from answering previous questions, resulting in superior performance with +7.2% F1 on CoQA and +4.0% on QuAC, and improvements of +1.8% to +4.4% accuracy on SCONE domains.
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.