posted by user: muhaochen || 875 views || tracked by 3 users: [display]

Frontiers in Big Data 2022 : Frontiers in Big Data Journal - Special Issue on Representation and Learning for Structured Knowledge

FacebookTwitterLinkedInGoogle

Link: https://www.frontiersin.org/research-topics/22803/representation-and-learning-for-structured-knowledge#overview
 
When Jan 1, 2022 - Jan 1, 2022
Where NA
Submission Deadline Nov 30, 2021
Categories    representation learning   knowledge graph   heterogeneous information netw   natural language understanding
 

Call For Papers

Part of human’s understanding of the world can be stored as various kinds of graph-structured representations, such as knowledge graphs, lexical graphs, product graphs, social networks, and biological networks. The essence of such structured knowledge representation is to provide a way of modeling the diverse types of relations for entities, concepts, and human language components, as well as interactions between molecules and biomolecules in nature. Accordingly, those sources of actionable knowledge are key to the support of many knowledge-aware intelligent systems for natural language understanding, e-commerce recommendation, social media analysis, and in silico research for biology and medicine. Particularly in this era of big data where intelligent systems are usually data-driven and learning-based, structured knowledge often supports the systems with stronger reasoning abilities and better robustness against reporting bias.

This article collection targets cutting edge research efforts that address three key problems for representation and learning of structured knowledge: (i) Knowledge acquisition: data-driven methods for acquiring structured knowledge from unstructured data, aligning and synchronizing the knowledge among different sources of data; (ii) Knowledge-based inference: inference of proximity, types and relations, as well as prediction and verification of missing knowledge; (iii) Knowledge-based application: successful ways of applying structured knowledge representations in downstream applications.

Detailed topics of interest include but not limited to the following:
–Representation and resources of structured knowledge: techniques for the semantic web; knowledge graph construction; domain-specific or application-driven knowledge graph; symbolic or distributional knowledge representations; causal graph inference; physical graph construction.
–Learning and inference of structured knowledge: fundamental research of representation learning, relational learning, and reasoning with constraints of relations; techniques for knowledge graph completion, entity type inference, anomaly detection.
–Integration and synchronization of structured knowledge: fundamental research of entity resolution, knowledge graph alignment and network matching; techniques for data integration between structured data, or grounding of unstructured data to structured data.
–Structured knowledge discovery in data analytics: information extraction including entity typing, named entity recognition, entity linking, relation extraction, event detection and extraction; ontology induction; scene graph generation; visual relation detection.
–Structured knowledge for natural language processing: Knowledge base question answering, knowledge-enhanced chatbot; zero-shot classification with knowledge; few-shot learning with knowledge; improving the models’ generalization ability with knowledge; knowledge-enhanced information extraction; defending adversarial attack with knowledge.
–Structured knowledge in computational biology and medicine research: drug discovery; molecule property classification; chemical reaction prediction; molecule graph generation; protein-protein-interaction/drug-drug-interaction/drug-target-interaction prediction.

Keywords: Representation Learning, Knowledge Graph, Heterogeneous Information Network, Natural Language Understanding


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

About Frontiers Research Topics
With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Related Resources

SoCAV 2023   2023 International Symposium on Connected and Autonomous Vehicles (SoCAV 2023)
MLDM 2023   18th International Conference on Machine Learning and Data Mining
IEEE SSCI 2023   2023 IEEE Symposium Series on Computational Intelligence
ICACII 2023   2nd International Conference on Advances in Computational Intelligence and Informatics
ICDM 2023   23rd Industrial Conference on Data Mining
SI PMABD 2023   Special Issue on Programming Models and Algorithms for Big Data
AI-DH 2022   MDPI Big Data and Cognitive Computing - Special Issue on Artificial Intelligence in Digital Humanities
DT4CS 2023   Special Issue on Digital Twins for Complex Systems in Big Data and Cognitive Computing Journal
ICCDA 2023   2023 The 7th International Conference on Compute and Data Analysis (ICCDA 2023)
ICMT 2023   2023 International Conference on Metaverse Technology (ICMT 2022)