Relation Classification via LSTMs Based on Sequence and Tree Structure

The goal of relation classification is to recognize the relationship between two marked entities in a sentence. It is a crucial constituent in natural language processing. Up till the present moment, most previous neural network models for this task either focus on using the handcrafted syntactic features or learning semantic representations of raw word sequences, they have no capacity for encoding the whole sentence representation including syntax and semantic information. In general, information of syntax and semantics can both have significant effect on classifying relation. Based on this idea, we propose a novel two-channel neural network architecture with attention mechanism in the paper to handle this task. First, we employ bidirectional sequence long short-term memory (LSTM) channel to capture the semantic information and acquire syntactic knowledge by utilizing tree structure LSTM channel. Second, sentence-level attention mechanism for word sequences is used to determine which parts of the sentence are most influential component. Eventually, we conduct experiments on two real-world datasets: the Wikipedia and the SemEval-2010 Task8 dataset. The experimental results on datasets demonstrate that our method can make better use of the information contained in sentences and achieves impressive improvements on relation classification as compared with the existing methods.