About Me

Hi! I am an undergraduate student in IEEE Honour Class, SJTU, majored in computer science. I’m curious about technology and knowledge and always motivate myself to learn and try new things. I know a little about both deep learning and blockchain and long for exporing more about them.

Research Interest

Deep Learning, Reinforcement Learning, Data Mining, Nature Language Processing, Knowledge Graph and Security.

Publications

1. Yining Hong, Jialu Wang, Yuting Jia, Weinan Zhang, Xinbing Wang. Academic Reader: An Interactive Question Answering System on Academic Literatures. In AAAI 2019 Demonstration Program.
2. Ruijie Wang, Yuchen Yan, Jialu Wang, Yuting Jia, Ye Zhang, Weinan Zhang, and Xinbing Wang. Acekg: A large-scale knowledge graph for academic data mining. In Proceedings of the 2018 ACM on Conference on Information and Knowledge Management CIKM 2018.
3. Chen Wang, Xiangyu Chen, Zelin Ye, Jialu Wang, Ziruo Cai, Shixiang Gu, and Cewu Lu. Trl: Discriminative hints for scalable reverse curriculum learning. In Deep Reinforcement Learning Symposium, NIPS 2017.

Projects

Learning to Read Academic Literature

Machine reading comprehension (MRC), which requires machines to answer questions about a given context, has attracted much attention in recent years. However, academic literature is still beyond the scope of state-of-the-art MRC systems, rendering an MRC task on academic literature strongly needed. In this paper, we propose PaperQA, a novel dataset focusing on the corpus of research papers on machine learning. PaperQA consists of over 12,000 question-answer pairs posed by crowdworkers on a set of over 12,000 question-answer pairs posed by crowdworkers on a set of over 1,800 academic abstracts. To better incorporate semantic information, we design a new model which utilizes the shared query aware context representation as the base of sentence ranking and answer extraction. Experimental evaluations show that our model outperforms state-of-the-art MRC models on this task. Our work helps to develop services on academic QA and benefits researchers by saving much time on paper scanning.

AceKG: A Large-scale Knowledge Graph for Academic Data Mining

As knowledge graph plays a more and more important role in this artificial intelligence era, many research groups are trying to organize the knowledge in their domain into a machine-readable knowledge graph, which stores knowledge in triple. Acemap Knowledge Graph (AceKG), supported by Acemap, is now open to everyone for research and non-commercial use. We hope this knowledge graph will benefit the research and development for academic data mining.

Acemap: A Mapmatic Academic System

Acemap is a gallery of academic maps visulizing authors, papers, topics and etc, makes people easier to do research. I have joined many work of the system, including writing the backend code, maintaining the web server, deploying the search engine, finding rising star and building the knowledge graph.

Skills

• Programming Language: C++, Python, Perl, Haskell, Java, Golang, Julia.
• Framework: Tensorflow, PyTorch, MXNet.

Contact Me

Jialu Wang

IEEE Honor Class, Shanghai Jiao Tong University

Office: 1-432 SEIEE Building, 800 Dongchuan Rd, Shanghai, China 200240

Email: faldict [at] sjtu[dot]edu[dot]cn