Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks
This work addresses the challenge of improving question answering accuracy by better modeling sentence relationships, though it is incremental as it builds on existing graph neural network methods.
The paper tackles the problem of detecting supporting sentences for question answering by proposing a graph neural network that propagates information between sentences to capture intersentential relationships, achieving state-of-the-art performance on the HotpotQA dataset.
In this study, we propose a novel graph neural network called propagate-selector (PS), which propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation. First, we design a graph structure in which each node represents an individual sentence, and some pairs of nodes are selectively connected based on the text structure. Then, we develop an iterative attentive aggregation and a skip-combine method in which a node interacts with its neighborhood nodes to accumulate the necessary information. To evaluate the performance of the proposed approaches, we conduct experiments with the standard HotpotQA dataset. The empirical results demonstrate the superiority of our proposed approach, which obtains the best performances, compared to the widely used answer-selection models that do not consider the intersentential relationship.