CS Events Monthly View
Computer Science Department ColloquiumData Analytics with Heterogeneous Supervision |
|
||
Tuesday, March 22, 2016, 10:30am |
|||
While unprecedented amounts of data are now readily available, it is
often not clear how to exploit these forms of data for machine learning,
natural language processing, and artificial intelligence. In this talk,
I will describe a series of results on methods that integrate and learn
from multiple, possibly quite heterogeneous kinds of data. In natural
language processing, for instance, these allow us to produce massively
multilingual word representations, covering over 200 languages. Combined
with data integration methods, we can also produce representations of
entities and large-scale knowledge graphs such as UWN/MENTA, one of the
largest multilingual taxonomies, and Lexvo.org, a major hub in the Web
of Data. Finally, I will outline new methods for mining from multiple
modalities, including images and video, that have the potential to take
us towards cognitive computing.
Speaker: Gerard de Melo
Bio
Gerard de Melo is a Tenure-Track Assistant Professor at TsinghuaUniversity, Beijing, where he is heading the Web Mining and LanguageTechnology group. He has published over 60 research papers in theseareas, with Best Paper awards at CIKM 2010, ICGL 2
Location : Core A (Room 301)
Committee:
Dimitris Metaxas
Event Type: Computer Science Department Colloquium
:
Organization:
Tsinghua University, Beijing