不知不觉,研究英文事件抽取两年了,是时候将看过的paper做一个总结了
目前事件抽取仍然集中于基于表示的神经网络方法,但基于特征的方法仍然值得去领悟,因此我主要按这两个类别进行分类:
基于特征的方法
2006_ACL_The Stages of Event Extraction
2008_ACL_Refining Event Extractionthrough Cross-document Inference
2010_ACL_Using Document Level Cross-Event Inference to IMprove Event Extraction
2011_ACL_Using Cross-Entity Inference to Improve Event Extraction
2013_ACL_Joint Event Extraction via Structured Prediction with Global Features
2016_AAAI_A Probabilistic Soft Logic Based Approach to Exploiting Latent and Global Information in Event Classification
基于表示的神经网络方法
2015_ACL_Event Detection and Domain Adaptation with Convolutional Neural Networks
2015_ACL_Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks
2016_ACL_A Language-Independent Neural Network for Event Detection
2016_ACL_Leveraging FrameNet to Improve Automatic Event