Special Issue on Knowledge Acquisition and Reasoning
Published 07 January, 2021
In 2012, Google proposed the concept of the knowledge graph, which describes mass entities and their relationships in a structured manner, enhancing semantic search and improving search quality. Since then, knowledge graph representation techniques, such as the state-of-the-art TransE, have emerged, expressing knowledge in continuous vectors to facilitate efficient reasoning.
However, there is a sparseness of knowledge graphs, especially common sense and domain knowledge graphs, which is hindering progress in this area. Geoffrey Hinton, Yoshua Bengio, and Yann LeCun, three Turing Prize winners, jointly wrote in Nature in 2015 that "major progress in artificial intelligence will come about through systems that combine representation learning with complex reasoning". In 2018, Zhang Bo, the Academician of the Chinese Academy of Sciences, pointed out that the third generation of artificial intelligence is an intelligent system that is explainable, robust, trusted, with knowledge at the core of the four elements. Increasingly, the study of neural symbol reasoning is becoming a hot research topic.
This special issue on knowledge acquisition and reasoning is devoted to gathering and presenting cutting-edge reviews, research and applications. Our aim is to provide a platform for researchers to share their recent observations and achievements in this active field.
Topics Covered:
- Knowledge representation
- Knowledge graph embedding
- Entity extraction, entity typing and relation extraction
- Open knowledge extraction
- Entity resolution and entity linking
- Knowledge graph completion
- Knowledge graph alignment
- Neural-symbolic reasoning
- Question answering on knowledge graphs
- Knowledge-enhanced search or recommendation
Important Deadlines:
- Submission deadline: 31 October 2021
Submission Instructions:
Papers submitted to this journal for possible publication must be original and must not be under consideration for publication in any other journals. At least 30% of extended work must comprise "new and original" ideas/contributions. Please read the Guide for Authors before submitting. All articles should be submitted online; please select SI: Knowledge Acquisition and Reasoning on submission.
Guest Editors:
- Dr. Jie Tang, Tsinghua University, China. Email: jietang@tsinghua.edu.cn
- Dr. Juanzi Li, Tsinghua University, China. Email: lijuanzi@tsinghua.edu.cn
- Dr. Jing Zhang, Renmin University of China, China. Email: zhang-jing@ruc.edu.cn
- Dr. Lei Hou, Tsinghua University, China, Email: houlei@tsinghua.edu.cn