BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering
This addresses the problem of complex reasoning over multiple documents for question answering, but it is incremental as it builds on existing graph and attention methods.
The paper tackled multi-hop reasoning question answering by proposing a Bi-directional Attention Entity Graph Convolutional Network (BAG), which achieved state-of-the-art accuracy on the QAngaroo WIKIHOP dataset.
Multi-hop reasoning question answering requires deep comprehension of relationships between various documents and queries. We propose a Bi-directional Attention Entity Graph Convolutional Network (BAG), leveraging relationships between nodes in an entity graph and attention information between a query and the entity graph, to solve this task. Graph convolutional networks are used to obtain a relation-aware representation of nodes for entity graphs built from documents with multi-level features. Bidirectional attention is then applied on graphs and queries to generate a query-aware nodes representation, which will be used for the final prediction. Experimental evaluation shows BAG achieves state-of-the-art accuracy performance on the QAngaroo WIKIHOP dataset.