- 1998.09 - 2002.07: Bachelor, Qufu Normal University, Shandong Province.
- 2002.09 - 2005.01: Master of Engineering, East of China Normal University, Shang Hai.
- 2013.09 - present: PhD Candidate, Renmin University of China, Beijing.
- 2005.01 - 2007.06: Assistant, Qufu Normal University, Shandong Province.
- 2007.06–2013.07: Lecturer, Qufu Normal University, Shandong Province.
Using Hybrid Algorithmic-Crowdsourcing Methods for
Academic Knowledge Acquisition
[under the supervisition of Prof.Jiaheng Lu]
Scientific literature contains a lot of meaningful objects such as Definitions, Algorithms, Figures, Tables, etc., which are called Knowledge Cells here. This makes it possible that a novel search engine returns a set of diverse Knowledge Cells, instead of a long list of relevant papers. Further, Knowledge Cells and their various relationships could help us to build an Academic Knowledge Graph to improve the performance of traditional academic search for information discovery and exploration. Therefore, it is important to identify and extract the Knowledge Cells and their various relationships which are often intrinsic and implicit in articles. With the exponential growth of scientific publications, discovery and acquisition of such useful academic knowledge poses many practical challenges. For example, existing algorithmic methods can hardly extend to handle diverse layouts of journals, nor to scale up to process massive documents. As crowdsourcing has become a powerful paradigm for large scale problem-solving especially for tasks that are difficult for computers but easy to human, we consider the problem of academic knowledge discovery and acquisition as a crowd-sourced database problem and show a hybrid framework to integrate the accuracy of crowd sourcing workers and the speed of automatic algorithms. In this paper, we introduce our current system implementation, a Platform for Academic kNowledge Discovery and Acquisition (PANDA), as well as some interesting observations and promising future directions.
Knowledge Graph Completion with Crowdsourcing Methods
A large number of Knowledge Bases have been created including Google Knowledge Graph and they are extremely useful for many applications. Although a typical KB may contain millions of entities or billions of relational facts, it is usually far from complete. Knowledge graph completion aims to find new relations between entities based on the existing knowledge graph, it needs to not only determine whether two entities have a relation or not, but also predict the specific type of the relation. In this research, we focus on knowledge graph completion using crowdsourcing method.
- Zhaoan Dong, Jiaheng Lu, Tok Wang Ling:PANDA: A platform for academic knowledge discovery and acquisition. BigComp 2016: 10-17 [PDF paper ] [Slide]
- Zhaoan Dong, Jiaheng Lu, Tok Wang Ling: Crowd-PANDA:Using Crowdsourcing Method for Academic Knowledge Acquisition WAIM 2016: 531-533 [Demo paper ][code] [poster]
- Feiran Huang, Jia Li, Jiaheng Lu, Tok Wang Ling,Zhaoan Dong:PandaSearch: A fine-grained academic search engine for research documents. ICDE 2015: 1408-1411
- Yueguo Chen, Xiongpai Qin, Haoqiong Bian, Jun Chen, Zhaoan Dong, Xiaoyong Du, Yanjie Gao, Dehai Liu, Jiaheng Lu, Huijie Zhang: A Study of SQL-on-Hadoop Systems. BPOE@ASPLOS/VLDB 2014: 154-166
Copyright © 2016. All rights reserved.