Hierarchical Graph Network for Multi-hop Question Answering

2019-11-09 · EMNLP 2020 11 · Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing Liu

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 BibTeX arXiv:1911.03631

Code (1)

yuwfan/HGN 공식 구현 pytorch

Tasks

Multi-hop Question Answering Question Answering

Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network

2020-04-20 · Guanming Xiong

In this paper, we present a two stage model for multi-hop question answering. The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of…

Graph Neural Network Language Modeling Language Modelling Multi-hop Question Answering+1

SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering

2026-01-06 · Junli Liang, Pengfei Zhou, Wangqiu Zhou, Wenjie Qing 외 arxiv

Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combin…

Multi-hop Question Answering Answer Generation

Graph Attention with Hierarchies for Multi-hop Question Answering

2023-01-27 · Yunjie He, Philip John Gorinski, Ieva Staliunaite, Pontus Stenetorp

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 …

Graph Attention Graph Neural Network Multi-hop Question Answering Question Answering+1

Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering

2018-11-29 · ACL 2018 7 · Wei Wang, Ming Yan, Chen Wu

This paper describes a novel hierarchical attention network for reading comprehension style question answering, which aims to answer questions for a given narrative paragraph. In the proposed method, attention and fusion…

Question Answering Reading Comprehension TriviaQA

GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering

2025-11-25 · Dionysia Danai Brilli, Dimitrios Mallis, Vassilis Pitsikalis, Petros Maragos arxiv

We propose GHR-VQA, Graph-guided Hierarchical Relational Reasoning for Video Question Answering (Video QA), a novel human-centric framework that incorporates scene graphs to capture intricate human-object interactions wi…

Video Question Answering Relational Reasoning