Relation Classification via Multi-Level Attention CNNs

By Linlin Wang, Zhu Cao, Gerard de Melo, Zhiyuan Liu. 2016

513 citations recorded by the source corpus.

Relation classification is a crucial ingredient in numerous information extraction systems seeking to mine structured facts from text. We propose a novel convolutional neural network architecture for this task, relying on two levels of attention in order to better discern patterns in heterogeneous contexts. This architecture enables endto-end learning from task-specific labeled data, forgoing the need for external knowledge such as explicit dependency structures. Experiments show that our model outperforms previous state-of-the-art methods, including those relying on much richer forms of prior knowledge.

Subfields: Artificial Intelligence, Model Architectures, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Zhiyuan Liu
  3. Maosong Sun
  4. Luke S. Zettlemoyer
  5. Percy Liang
  6. Jianfeng Gao
  7. Caiming Xiong
  8. Noah A. Smith

In Model Architectures

  1. Jiwei Li
  2. Christopher D. Manning
  3. Mo Yu
  4. Bowen Zhou
  5. Bing Xiang
  6. Chris Quirk
  7. C. D. Santos
  8. Yuhao Zhang

In Information Extraction

  1. Wen-tau Yih
  2. Jie Zhou
  3. Christopher D. Manning
  4. Yuhao Zhang
  5. Wei Dang Lu
  6. Bing Xiang
  7. Peng Li
  8. Xiaoyan Zhu

Citations in the corpus