I was a Research Staff Member in IBM Research-Almaden. I received my Ph.D. degree from Peking University supervised by Dr. Ming Zhang. I was also a visiting Ph.D. student at University of Illinois at Urbana-Champaign under the supervision of Dr. Jiawei Han.

I worked with Dr. Yangqiu Song from HKUST, Dr. Yizhou Sun from UCLA, Dr. Dan Roth from University of Pennsylvania, and Dr. Ming Zhou from Microsoft Research Asia.


My research interests span the areas of machine learning, natural language understanding and graph mining. The goal of my research is to help real world applications in human daily life with better intelligence. To achieve this goal, I am now working on machine learning with indirect supervision and its applications to deep language understanding, as well as to graph construction and representation learning, enabling machine to better understand human.

I am enthusiastic to contribute to open source projects including:

Selected Publications [Full List]

Language models with Transformers
Chenguang Wang, Mu Li, and Alexander Smola.
In arXiv preprint arXiv:1904.09408 (arXiv 2019).
[paper] [code] [slides]

Gets more than 4.4k blog views and more than 320 Likes and Retweets on Twitter. Experimental results on the PTB, WikiText-2, and WikiText-103 show that proposed method achieves perplexities between 20.42 and 34.11 on all problems, i.e. on average an improvement of 12.0 perplexity units compared to state-of-the-art LSTMs.

Crowd-in-the-loop: A hybrid approach for annotating semantic roles
Chenguang Wang, Alan Akbik, Laura Chiticariu, Yunyao Li, Fei Xia, and Anbang Xu.
In Proc. 2017 Conf. on Empirical Methods on Natural Language Processing (EMNLP 2017).
[paper] [data] [slides]

Our experimental evaluation shows that the proposed approach reduces the workload for experts by over two-thirds, and thus significantly reduces the cost of producing SRL annotation at little loss in quality.

Incorporating world knowledge to document clustering via heterogeneous information networks
Chenguang Wang, Yangqiu Song, Ahmed El-Kishky, Dan Roth, Ming Zhang, and Jiawei Han.
In Proc. 2015 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD 2015).
[paper] [slides] [video] [code] [data]

We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network.