This is a past event
Venue: Room 234 (CSD Common Room), Meston Building
Title: Incorporating World Knowledge to Heterogeneous Information Networks
Abstract:
One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts. We consider the framework to use the world knowledge as indirect supervision. World knowledge is general-purpose knowledge, which is not designed for any specific domain. Then the key challenges are how to adapt the world knowledge to domains and how to represent it for learning. In this talk, we provide an example of using world knowledge for domain dependent text mining. We 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. In the experiments, we use two existing knowledge bases as our sources of world knowledge. One is Freebase, which is collaboratively collected knowledge about entities and their organizations. The other is YAGO2, a knowledge base automatically extracted from Wikipedia and maps knowledge to the linguistic knowledge base, WordNet. Experimental results show that incorporating world knowledge as indirect supervision can significantly outperform the state-of-art machine learning algorithms.
Brief Bio:
Ming Zhang is a full professor at the School of Electronics Engineering and Computer Science at Peking University. Prof. Zhang is the vice director of CCF Educational Committee, a member of ACM Education Council and the Chair of ACM SIGCSE China and a member of the ACM/IEEE CC2020 steering group. She has published more 200 research papers on Text Mining and Artificial Intelligence in the top journals and conferences, such as ICML, KDD, AAAI, IJCAL, ACL, WWW and TKDE. She won the best paper of ICML 2014 and best paper nominee of WWW 2016. Her paper on network embedding is the most cited paper in WWW 2015 proceedings. Prof. Zhang is the leading author of several textbooks on Data Structures and Algorithms in Chinese, and the corresponding course is awarded as the National Elaborate Course by MOE China. Ming Zhang received her Bachelor, Master and PhD degrees in Computer Science from Peking University respectively.
- Speaker
- Zhang Ming (Beijing University, China)
- Hosted by
- Dr Jeff Pan
- Venue
- MT234