FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
arXiv:1908.05117
Abstract
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.
arXiv commentAccepted by the 2nd Workshop on Machine Reading for Question Answering (MRQA), EMNLP 2019 Workshop
References in corpus (6)
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
- Simpler Context-Dependent Logical Forms via Model Projections
- Unified Pragmatic Models for Generating and Following Instructions
- A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC
Cited by in corpus (4)
- GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
- Weakly-Supervised Open-Retrieval Conversational Question Answering
- BERT-CoQAC: BERT-based Conversational Question Answering in Context
- Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering