GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
This work addresses the problem of effectively utilizing conversation history for conversational machine comprehension, which is crucial for handling coreference and ellipsis in dialogues, representing an incremental improvement over existing methods.
The paper tackles the challenge of conversational machine comprehension by proposing GraphFlow, a model that dynamically constructs context graphs and uses a recurrent graph neural network with a flow mechanism to capture conversational flow, achieving competitive performance on CoQA, QuAC, and DoQA benchmarks.
Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture conversation history and thus have trouble handling questions involving coreference or ellipsis. Moreover, when reasoning over passage text, most of them simply treat it as a word sequence without exploring rich semantic relationships among words. In this paper, we first propose a simple yet effective graph structure learning technique to dynamically construct a question and conversation history aware context graph at each conversation turn. Then we propose a novel Recurrent Graph Neural Network, and based on that, we introduce a flow mechanism to model the temporal dependencies in a sequence of context graphs. The proposed GraphFlow model can effectively capture conversational flow in a dialog, and shows competitive performance compared to existing state-of-the-art methods on CoQA, QuAC and DoQA benchmarks. In addition, visualization experiments show that our proposed model can offer good interpretability for the reasoning process.