FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
This addresses the challenge of understanding dialogue flow in conversational QA, though it appears incremental as it builds on prior work like FlowQA.
The paper tackles the problem of conversational machine comprehension by explicitly modeling information gain through dialogue reasoning, achieving state-of-the-art performance on the QuAC and SCONE datasets.
Conversational machine comprehension requires deep understanding of the dialogue flow, and the prior work proposed FlowQA to implicitly model the context representations in reasoning for better understanding. This paper proposes to explicitly model the information gain through dialogue reasoning in order to allow the model to focus on more informative cues. The proposed model achieves state-of-the-art performance in a conversational QA dataset QuAC and sequential instruction understanding dataset SCONE, which shows the effectiveness of the proposed mechanism and demonstrates its capability of generalization to different QA models and tasks.