Pairwise Relation Classification with Mirror Instances and a Combined Convolutional Neural Network

Jianfei Yu, Jing Jiang


Abstract
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 the SemEval-2010 Task 8 dataset. The empirical results show that with two additional features, our model achieves the state-of-the-art result of F1 score of 85.7.
Anthology ID:
C16-1223
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
2366–2377
Language:
URL:
https://aclanthology.org/C16-1223
DOI:
Bibkey:
Cite (ACL):
Jianfei Yu and Jing Jiang. 2016. Pairwise Relation Classification with Mirror Instances and a Combined Convolutional Neural Network. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2366–2377, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Pairwise Relation Classification with Mirror Instances and a Combined Convolutional Neural Network (Yu & Jiang, COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/C16-1223.pdf