Neural Networks (NN) have been applied successfully to many Information Extraction (IE) tasks recently. However, most of the current models are designed for a separate task of the IE pipeline, focusing only on the local information specific to the task. Such local models are not able to capture the global information or the long range inter-dependencies between multiple prediction stages, that are necessary for many IE problems.
In this talk, I will present my recent research on memory augmented networks (MAN) to address such limitations of the local NN models. In such networks, memory tensors are introduced to accumulate the prediction information during the course of the local stages, and provide such global memory as additional evidence for the local predictions of IE. I will discuss the applications of MAN on two typical problems of IE, i.e, Event Extraction and Entity Linking, that highly demonstrate its benefits.
Thien Huu Nguyen is a Ph.D. candidate in the Computer Science Department at New York University (NYU). His long-term research goal is to create intelligent systems that can achieve a human level of understanding of natural languages. His Ph.D. research centers around the development of Deep Learning models for Information Extraction, including Relation Extraction, Event Extraction, Mention Detection, and Slot Filling. His research advisors at NYU are Professor Ralph Grishman and Professor Kyunghyun Cho.
Thien Huu Nguyen was a research intern at the IBM T.J. Watson Research Center (Yorktown Heights, New York) in the summers of 2015 and 2016, where he developed new neural network models for Mention Detection and Entity Linking. Thien is a recipient of the IBM Ph.D. fellowship (2016-2017) and he is expected to graduate in May 2017.