Bilingual Event Extraction: a Case Study on Trigger Type Determination
Zhu Zhu, Shoushan Li, Guodong Zhou, Rui Xia · 2014
Event extraction generally suffers from the data sparseness problem.In this paper, we address this problem by utilizing the labeled data from two different languages.As a preliminary study, we mainly focus on the subtask of trigger type determination in event extraction.To make the training data in different languages help each other, we propose a uniform text representation with bilingual features to represent the samples and handle the difficulty of locating the triggers in the translated text from both monolingual and bilingual perspectives.Empirical studies demonstrate the effectiveness of the proposed approach to bilingual classification on trigger type determination.