FlowDelta: Modeling ow information gain in reasoning for conversational machine comprehension

Published in The 2nd Workshop on Machine Reading for Question Answering (MRQA) in The 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019

Yi-Ting Yeh, and Yun-Nung Chen.

Full Paper: arXiv

Code: GitHub

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.