Pairwise relation classification with mirror instances and a combined convolutional neural network

• Main Authors: YU, Jianfei, Jing JIANG
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2016
• Subjects: Computational linguistics; Mirrors; Neural networks; Semantics; Text processing; Combined model; Convolutional neural network; Relation classifications; Semantic relations; State of the art; Classification (of information); Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/3435; https://ink.library.smu.edu.sg/context/sis_research/article/4436/viewcontent/coling2016.pdf
• Institution: Singapore Management University

Relation classification is the task of classifying the semantic relations between entity pairs in text. Observing that existing work has not fully explored using different representations for relation instances, especially in order to better handle the asymmetry of relation types, in this paper, we propose a neural network based method for relation classification that combines the raw sequence and the shortest dependency path representations of relation instances and uses mirror instances to perform pairwise relation classification. We evaluate our proposed models on two widely used datasets: SemEval-2010 Task 8 and ACE-2005. The empirical results show that our combined model together with mirror instances achieves the state-of-the-art results on both datasets.