FlowQA: Grasping Flow in History for Conversational Machine Comprehension

ICLR 2019 Hsin-Yuan HuangEunsol ChoiWen-tau Yih

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... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Question Answering CoQA FlowQA (single model) In-domain 76.3 # 5
Question Answering CoQA FlowQA (single model) Out-of-domain 71.8 # 5
Question Answering CoQA FlowQA (single model) Overall 75.0 # 5
Question Answering QuAC FlowQA (single model) F1 64.1 # 1
Question Answering QuAC FlowQA (single model) HEQQ 59.6 # 1
Question Answering QuAC FlowQA (single model) HEQD 5.8 # 1