Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering

Zhenyun Deng, Yonghua Zhu, Qianqian Qi, Michael Witbrock, Patricia Riddle


Abstract
Current graph-neural-network-based (GNN-based) approaches to multi-hop questions integrate clues from scattered paragraphs in an entity graph, achieving implicit reasoning by synchronous update of graph node representations using information from neighbours; this is poorly suited for explaining how clues are passed through the graph in hops. In this paper, we describe a structured Knowledge and contextual Information Fusion GNN (KIFGraph) whose explicit multi-hop graph reasoning mimics human step by step reasoning. Specifically, we first integrate clues at multiple levels of granularity (question, paragraph, sentence, entity) as nodes in the graph, connected by edges derived using structured semantic knowledge, then use a contextual encoder to obtain the initial node representations, followed by step-by-step two-stage graph reasoning that asynchronously updates node representations. Each node can be related to its neighbour nodes through fused structured knowledge and contextual information, reliably integrating their answer clues. Moreover, a masked attention mechanism (MAM) filters out noisy or redundant nodes and edges, to avoid ineffective clue propagation in graph reasoning. Experimental results show performance competitive with published models on the HotpotQA dataset.
Anthology ID:
2022.dlg4nlp-1.8
Volume:
Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)
Month:
July
Year:
2022
Address:
Seattle, Washington
Venue:
DLG4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
71–80
Language:
URL:
https://aclanthology.org/2022.dlg4nlp-1.8
DOI:
10.18653/v1/2022.dlg4nlp-1.8
Bibkey:
Cite (ACL):
Zhenyun Deng, Yonghua Zhu, Qianqian Qi, Michael Witbrock, and Patricia Riddle. 2022. Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering. In Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022), pages 71–80, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering (Deng et al., DLG4NLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.dlg4nlp-1.8.pdf
Code
 tswinggg/kifgraph
Data
HotpotQA