IECAS Event Detection System at TAC KBP 2017 Event Nugget Track

This paper describes our Event Nugget Detection systems that we submitted to the TAC KBP 2017 Event Track. We implement pipelined event detection systems based on convolutional neural network (CNN) and bidirectional Long Short-Term Memery (BiLSTM) for both event type and realis classification. Our systems use only word embeddings as external resources for training so they can be easily adapted to multiple languages. The experimental results show that our approaches can achieve promising performances in the Event Nugget Detection task.