Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees

We present a novel attention-based recurrent neural network for joint extraction of entity mentions and relations. We show that attention along with long short term memory (LSTM) network can extract semantic relations between entity mentions without having access to dependency trees. Experiments on Automatic Content Extraction (ACE) corpora show that our model significantly outperforms featurebased joint model by Li and Ji (2014). We also compare our model with an end-toend tree-based LSTM model (SPTree) by Miwa and Bansal (2016) and show that our model performs within 1% on entity mentions and 2% on relations. Our finegrained analysis also shows that our model performs significantly better on AGENTARTIFACT relations, while SPTree performs better on PHYSICAL and PARTWHOLE relations.