Event Nugget Detection with Forward-Backward Recurrent Neural Networks
This work addresses event detection in natural language processing, specifically for multi-word events, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting events that can be single words or phrases, which traditional and recent deep learning methods had not addressed, and shows that their forward-backward recurrent neural network (FBRNN) approach is competitive with state-of-the-art methods on ACE 2005 and Rich ERE 2015 tasks.
Traditional event detection methods heavily rely on manually engineered rich features. Recent deep learning approaches alleviate this problem by automatic feature engineering. But such efforts, like tradition methods, have so far only focused on single-token event mentions, whereas in practice events can also be a phrase. We instead use forward-backward recurrent neural networks (FBRNNs) to detect events that can be either words or phrases. To the best our knowledge, this is one of the first efforts to handle multi-word events and also the first attempt to use RNNs for event detection. Experimental results demonstrate that FBRNN is competitive with the state-of-the-art methods on the ACE 2005 and the Rich ERE 2015 event detection tasks.