Relation Classification Using Segment-Level Attention-based CNN and Dependency-based RNN
Van-Hien Tran, Van-Thuy Phi, Hiroyuki Shindo, Yuji Matsumoto
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
Recently, relation classification has gained much success by exploiting deep neural networks. In this paper, we propose a new model effectively combining Segment-level Attention-based Convolutional Neural Networks (SACNNs) and Dependency-based Recurrent Neural Networks (DepRNNs). While SACNNs allow the model to selectively focus on the important information segment from the raw sequence, DepRNNs help to handle the long-distance relations from the shortest dependency path of relation entities. Experiments on the SemEval-2010 Task 8 dataset show that our model is comparable to the state-of-the-art without using any external lexical features.