New York University 2016 System for KBP Event Nugget: A Deep Learning Approach

This is the first time New York University (NYU) participates in the event nugget (EN) evaluation of the Text Analysis Conference (TAC). We developed EN systems for both subtasks of event nugget, i.e, EN Task 1: Event Nugget Detection and EN Task 2: Event Nugget Detection and Coreference. The systems are mainly based on our recent research on deep learning for event detection (Nguyen and Grishman, 2015a; Nguyen and Grishman, 2016a). Due to the limited time we could devote to system development this year, we only ran the systems on the English evaluation data. However, we expect that the adaptation of the current systems to new languages can be done quickly. The development experiments show that although our current systems do not rely on complicated feature engineering, they significantly outperform the reported systems last year for the EN subtasks on the 2015 evaluation data.