@inproceedings{deng-etal-2022-explicit,
title = "Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering",
author = "Deng, Zhenyun and
Zhu, Yonghua and
Qi, Qianqian and
Witbrock, Michael and
Riddle, Patricia",
editor = "Wu, Lingfei and
Liu, Bang and
Mihalcea, Rada and
Pei, Jian and
Zhang, Yue and
Li, Yunyao",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dlg4nlp-1.8",
doi = "10.18653/v1/2022.dlg4nlp-1.8",
pages = "71--80",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2022-explicit">
<titleInfo>
<title>Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhenyun</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonghua</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Witbrock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Riddle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingfei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">deng-etal-2022-explicit</identifier>
<identifier type="doi">10.18653/v1/2022.dlg4nlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2022.dlg4nlp-1.8</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>71</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering
%A Deng, Zhenyun
%A Zhu, Yonghua
%A Qi, Qianqian
%A Witbrock, Michael
%A Riddle, Patricia
%Y Wu, Lingfei
%Y Liu, Bang
%Y Mihalcea, Rada
%Y Pei, Jian
%Y Zhang, Yue
%Y Li, Yunyao
%S Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F deng-etal-2022-explicit
%X 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.
%R 10.18653/v1/2022.dlg4nlp-1.8
%U https://aclanthology.org/2022.dlg4nlp-1.8
%U https://doi.org/10.18653/v1/2022.dlg4nlp-1.8
%P 71-80
Markdown (Informal)
[Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering](https://aclanthology.org/2022.dlg4nlp-1.8) (Deng et al., DLG4NLP 2022)
ACL