Conference Proceeding Article
Relation classification is the task of classifying the semantic relations between entity pairs intext. Observing that existing work has not fully explored using different representations forrelation instances, especially in order to better handle the asymmetry of relation types, in thispaper, we propose a neural network based method for relation classification that combines theraw sequence and the shortest dependency path representations of relation instances and usesmirror instances to perform pairwise relation classification. We evaluate our proposed modelson two widely used datasets: SemEval-2010 Task 8 and ACE-2005. The empirical results showthat our combined model together with mirror instances achieves the state-of-the-art results onboth datasets.
Databases and Information Systems | Systems Architecture
Data Management and Analytics
Proceedings of COLING 2016: The 26th International Conference on Computational Linguistics: Technical Papers, Japan, 2016 December 11-17
City or Country
YU, JIANFEI and Jing JIANG.
Pairwise relation classification with mirror instances and a combined convolutional neural network. (2016). Proceedings of COLING 2016: The 26th International Conference on Computational Linguistics: Technical Papers, Japan, 2016 December 11-17. 2373-2377. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3435
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.