Graph Attention with Hierarchies for Multi-hop Question Answering

01/27/2023
by   Yunjie He, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/09/2019

Hierarchical Graph Network for Multi-hop Question Answering

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop...
research
04/20/2020

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

In this paper, we present a two stage model for multi-hop question answe...
research
05/24/2022

From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering

Multi-hop question answering (QA) is a challenging task requiring QA sys...
research
04/15/2021

TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph

Multi-hop Question Answering (QA) is a challenging task because it requi...
research
05/23/2019

Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal

Reading Comprehension has received significant attention in recent years...
research
10/07/2020

SRLGRN: Semantic Role Labeling Graph Reasoning Network

This work deals with the challenge of learning and reasoning over multi-...
research
07/01/2023

Single Sequence Prediction over Reasoning Graphs for Multi-hop QA

Recent generative approaches for multi-hop question answering (QA) utili...

Please sign up or login with your details

Forgot password? Click here to reset