Hierarchical Graph Network for Multi-hop Question Answering

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of granularity (questions, paragraphs, sentences, entities), the representations of which are initialized with pre-trained contextual encoders. Given this hierarchical graph, the initial node representations are updated through graph propagation, and multi-hop reasoning is performed via traversing through the graph edges for each subsequent sub-task (e.g., paragraph selection, supporting facts extraction, answer prediction). By weaving heterogeneous nodes into an integral unified graph, this hierarchical differentiation of node granularity enables HGN to support different question answering sub-tasks simultaneously. Experiments on the HotpotQA benchmark demonstrate that the proposed model achieves new state of the art, outperforming existing multi-hop QA approaches.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering HotpotQA HGN + SemanticRetrievalMRS IR ANS-EM 0.567 # 36
ANS-F1 0.692 # 38
SUP-EM 0.500 # 20
SUP-F1 0.764 # 28
JOINT-EM 0.356 # 25
JOINT-F1 0.599 # 33

Methods


No methods listed for this paper. Add relevant methods here