UIUC

Abstract:

We present a novel sequence labeling model based on the latent-variable semi-Markov conditional random fields for jointly extracting argument roles of events from texts. The model takes in coarse mention and type information and predicts argument roles for a given event template.

We addresses the event extraction problem in a primarily unsupervised setting, where no labeled training instances are available. Our key contribution is a novel learning framework called structured preference modeling (PM), that allows arbitrary preference to be assigned to certain structures during the learning procedure. We establish and discuss connections between this framework and other existing works. We show empirically that the structured preferences are crucial to the success of our task. Our model, trained without annotated data and with a small number of structured preferences, yields performance competitive to some baseline supervised approaches.

This is a joint work with Dan Roth.


Bio:
Dr. Wei Lu obtained his BS, MS, and PhD from the National University of Singapore (NUS) in 2005, 2006 and 2009 respectively. He was a visiting student to MIT in 2007-2008. He received the best paper award at EMNLP'11. Currently he is working as a postdoctoral research associate with Professor Dan Roth.