论文信息 - Hybrid BiLSTM-Siamese Network for Relation Extraction

Hybrid BiLSTM-Siamese Network for Relation Extraction

Relation extraction is an important processing task in knowledge graph completion. In previous approaches, it is considered to be a multi-class classification problem. In this paper, we propose a novel approach called hybrid BiLSTM-Siamese network which combines two word-level bidirectional LSTMs by a Siamese model architecture. It learns a similarity metric between two sentences and predicts the relation of a new sentence by k-nearest neighbors' algorithm. In experiments, we use the SemEval-2010 Task8 dataset and achieve an F1-score of 81.8%.

[1] Jun Zhao,et al. Relation Classification via Convolutional Deep Neural Network , 2014, COLING.

[2] Wei Shi,et al. Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification , 2016, ACL.

[3] Andrew Y. Ng,et al. Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[4] Dongyan Zhao,et al. Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling , 2015, EMNLP.

[5] Houfeng Wang,et al. Bidirectional Recurrent Convolutional Neural Network for Relation Classification , 2016, ACL.

[6] Zhi Jin,et al. Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths , 2015, EMNLP.

[7] Takashi Chikayama,et al. Simple Customization of Recursive Neural Networks for Semantic Relation Classification , 2013, EMNLP.