Graph Attention with Hierarchies for Multi-hop Question Answering
This work addresses multi-hop QA, a complex task in natural language processing, by proposing incremental improvements to an existing model for better accuracy on a specific benchmark.
The paper tackled multi-hop question answering on the HotpotQA benchmark by extending a state-of-the-art Graph Neural Network model with new query-context edges and a hierarchical graph attention mechanism, achieving improved performance as demonstrated in experiments.
Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as well as a few standard benchmarks to assess models Multi-hop QA capabilities. In this paper, we focus on the well-established HotpotQA benchmark dataset, which requires models to perform answer span extraction as well as support sentence prediction. We present two extensions to the SOTA Graph Neural Network (GNN) based model for HotpotQA, Hierarchical Graph Network (HGN): (i) we complete the original hierarchical structure by introducing new edges between the query and context sentence nodes; (ii) in the graph propagation step, we propose a novel extension to Hierarchical Graph Attention Network GATH (Graph ATtention with Hierarchies) that makes use of the graph hierarchy to update the node representations in a sequential fashion. Experiments on HotpotQA demonstrate the efficiency of the proposed modifications and support our assumptions about the effects of model related variables.