Relation Classification Via Modeling Augmented Dependency Paths

• Published in: IEEE/ACM transactions on audio, speech, and language processing speech, and language processing, 2016-09, Vol.24 (9), p.1589-1598
• Main Authors: Liu, Yang, Li, Sujian, Wei, Furu, Ji, Heng
• Format: Article
• Language: English
• Subjects: Classification; Convolution neural network; dependency subtree; Feature extraction; IEEE transactions; Instruments; Kernel; Natural language processing; Neural networks; Recurrent neural networks; Recursive; recursive neural network; relation classification; Representations; Semantics; shortest dependency path; Shortest-path problems; Speech
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2016.2573050

Previous research on relation classification has verified the effectiveness of using dependency shortest paths or dependency subtrees. How to efficiently unify these two kinds of dependency information in relation classification is still an open problem. In this paper, we propose a novel structure, termed augmented dependency path (ADP), which is composed of the shortest dependency path between two entities and the subtrees attached to the shortest path. To exploit the semantic representation behind the ADP structure, we develop the dependency-based neural networks (DepNN) model which combines the advantages of the recursive neural network (RNN) and the convolutional neural network (CNN). In DepNN, RNN is designed to model the dependency subtrees since it is good at capturing the hierarchical structures. Then, the semantic representation in subtrees is passed to the nodes on the shortest path and CNN is used to get the most important features on the ADP. Experiments on the SemEval-2010 dataset show that the ADP structure including both the shortest dependency path and the attached subtrees is helpful to classify the semantic relations between two entities and our proposed method can achieve the state-of-the-art performance.