End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
Makoto Miwa, Mohit Bansal · 2016
We present a novel end-to-end neural model to extract entities and relations between them.Our recurrent neural network based model captures both word sequence and dependency tree substructure information by stacking bidirectional treestructured LSTM-RNNs on bidirectional sequential LSTM-RNNs.This allows our model to jointly represent both entities and relations with shared parameters in a single model.We further encourage detection of entities during training and use of entity information in relation extraction via entity pretraining and scheduled sampling.Our model improves over the stateof-the-art feature-based model on end-toend relation extraction, achieving 12.1% and 5.7% relative error reductions in F1score on ACE2005 and ACE2004, respectively.We also show that our LSTM-RNN based model compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).Finally, we present an extensive ablation analysis of several model components.