Query Path Generation via Bidirectional Reasoning for Multihop Question Answering From Knowledge Bases

计算机科学 限制 知识图 关系(数据库) 封面(代数) 答疑 路径(计算) 知识库 知识表示与推理 召回 图形 代表(政治) 编码(内存) 理论计算机科学 人工智能 数据挖掘 机械工程 工程类 语言学 哲学 政治 法学 政治学 程序设计语言
作者
Geng Zhang,Jin Liu,Guangyou Zhou,Zhiwen Xie,Xiao Yu,Xiaohui Cui
出处
期刊:IEEE Transactions on Cognitive and Developmental Systems [Institute of Electrical and Electronics Engineers]
卷期号:15 (3): 1183-1195 被引量:9
标识
DOI:10.1109/tcds.2022.3198272
摘要

Multihop question answering from knowledge bases (KBQA) is a hot research topic in natural language processing. Recently, the graph neural network-based (GNN-based) methods have achieved promising results as the KB can be organized as a knowledge graph (KG). However, they often suffered from the sparsity of the KG which was detrimental to the structure encoding and reasoning capabilities of GNN. Specifically, a KG is a sparse graph linked by directed relations and previous studies have paid scant attention to the directional characteristic of relations in the KG, limiting the patterns of relation path that GNN-based approaches could resolve. This study proposes a bidirectional recurrent GNN (BRGNN) to tackle these difficulties. To model the bidirectional information of relations, all adjacent relations of an entity are grouped by their directions, and they are separately aggregated into the entity representation in outward and inward directions. For the reasoning process, BRGNN simultaneously considers the neighbor relations in both directions to cover more patterns of relation paths and improve the recall of answers. Extensive experiments on three benchmarks: WebQuestionsSP, ComplexWebQuestions, and MetaQA, verify that BRGNN can answer more questions by taking into account the directional information, and it is competitive to all state-of-the-art approaches.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
hugeyoung完成签到,获得积分10
刚刚
刚刚
耳百完成签到,获得积分10
1秒前
3秒前
4秒前
5秒前
6秒前
6秒前
CR7应助越啊采纳,获得20
7秒前
李健应助123采纳,获得10
8秒前
Jun完成签到,获得积分10
9秒前
大反应釜发布了新的文献求助10
9秒前
淳于安筠发布了新的文献求助30
12秒前
柳叶洋完成签到,获得积分10
12秒前
下一秒发布了新的文献求助10
15秒前
16秒前
17秒前
无花果应助科研通管家采纳,获得10
17秒前
Akim应助科研通管家采纳,获得10
17秒前
852应助科研通管家采纳,获得10
17秒前
SYLH应助科研通管家采纳,获得30
17秒前
斯文败类应助科研通管家采纳,获得10
17秒前
Owen应助科研通管家采纳,获得10
17秒前
orixero应助科研通管家采纳,获得10
17秒前
Orange应助科研通管家采纳,获得10
17秒前
情怀应助科研通管家采纳,获得30
17秒前
Jasper应助科研通管家采纳,获得10
18秒前
英俊的铭应助科研通管家采纳,获得10
18秒前
18秒前
Ava应助科研通管家采纳,获得10
18秒前
情怀应助科研通管家采纳,获得10
18秒前
18秒前
18秒前
18秒前
18秒前
SYLH应助shensiang采纳,获得20
19秒前
专一的从波完成签到 ,获得积分10
19秒前
领导范儿应助msjs采纳,获得30
19秒前
量子星尘发布了新的文献求助10
21秒前
安静的幼旋完成签到,获得积分10
22秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989444
求助须知:如何正确求助?哪些是违规求助? 3531531
关于积分的说明 11254250
捐赠科研通 3270191
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174