Hierarchical Graph Network for Multi-hop Question Answering
Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing, Liu

TL;DR
This paper introduces a Hierarchical Graph Network that effectively models multi-level textual information to improve multi-hop question answering, achieving state-of-the-art results on HotpotQA.
Contribution
The paper proposes a novel hierarchical graph structure with multi-level nodes for multi-hop QA, enabling simultaneous handling of various sub-tasks and outperforming existing methods.
Findings
Achieves new state-of-the-art on HotpotQA benchmark.
Effectively integrates multi-level textual clues for reasoning.
Supports multiple QA sub-tasks within a unified framework.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Multimodal Machine Learning Applications
