Event Nugget Detection with Forward-Backward Recurrent Neural Networks

TL;DR

This paper introduces a novel RNN-based approach for event detection that effectively identifies both single-word and multi-word events, outperforming traditional methods on standard benchmarks.

Contribution

It is the first to apply forward-backward RNNs to detect multi-word events, advancing automatic feature learning in event detection tasks.

Findings

FBRNN achieves competitive results on ACE 2005.

FBRNN outperforms traditional feature-engineered methods.

Handles multi-word event mentions effectively.

Abstract

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.