A comprehensive survey of graph neural networks for knowledge graphs
The Knowledge graph, a multi-relational graph that represents rich factual information
among entities of diverse classifications, has gradually become one of the critical tools for …
among entities of diverse classifications, has gradually become one of the critical tools for …
[HTML][HTML] Knowledge graph quality control: A survey
A knowledge graph (KG), a special form of semantic network, integrates fragmentary data
into a graph to support knowledge processing and reasoning. KG quality control is important …
into a graph to support knowledge processing and reasoning. KG quality control is important …
Transformer-xh: Multi-evidence reasoning with extra hop attention
Transformers have achieved new heights modeling natural language as a sequence of text
tokens. However, in many real world scenarios, textual data inherently exhibits structures …
tokens. However, in many real world scenarios, textual data inherently exhibits structures …
From alignment to assignment: Frustratingly simple unsupervised entity alignment
Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual
KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are …
KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are …
Unrestricted multi-hop reasoning network for interpretable question answering over knowledge graph
Abstract Knowledge graphs significantly boost the answer retrieval quality for natural
language questions. The knowledge graph based question answering (KGQA) task returns …
language questions. The knowledge graph based question answering (KGQA) task returns …
Dynamic semantic graph construction and reasoning for explainable multi-hop science question answering
Knowledge retrieval and reasoning are two key stages in multi-hop question answering (QA)
at web scale. Existing approaches suffer from low confidence when retrieving evidence facts …
at web scale. Existing approaches suffer from low confidence when retrieving evidence facts …
An effective and efficient entity alignment decoding algorithm via third-order tensor isomorphism
X Mao, M Ma, H Yuan, J Zhu, Z Wang… - Proceedings of the …, 2022 - aclanthology.org
Entity alignment (EA) aims to discover the equivalent entity pairs between KGs, which is a
crucial step for integrating multi-source KGs. For a long time, most researchers have …
crucial step for integrating multi-source KGs. For a long time, most researchers have …
Answering open-domain questions of varying reasoning steps from text
We develop a unified system to answer directly from text open-domain questions that may
require a varying number of retrieval steps. We employ a single multi-task transformer model …
require a varying number of retrieval steps. We employ a single multi-task transformer model …
Are negative samples necessary in entity alignment? An approach with high performance, scalability and robustness
Entity alignment (EA) aims to find the equivalent entities in different KGs, which is a crucial
step in integrating multiple KGs. However, most existing EA methods have poor scalability …
step in integrating multiple KGs. However, most existing EA methods have poor scalability …
Representation learning for knowledge fusion and reasoning in Cyber–Physical–Social Systems: Survey and perspectives
The digital deep integration of cyber space, physical space and social space facilitates the
formation of Cyber–Physical–Social Systems (CPSS). Knowledge empowers CPSS to be …
formation of Cyber–Physical–Social Systems (CPSS). Knowledge empowers CPSS to be …