Improving Relation Classification by Entity Pair Graph

Yi Zhao, Huaiyu Wan, Jianwei Gao, Youfang Lin
Proceedings of The Eleventh Asian Conference on Machine Learning, PMLR 101:1156-1171, 2019.

Abstract

Relation classification is one of the most important tasks in the field of information extraction, and also a key component of systems that require relational understanding of unstructured text. Existing relation classification approaches mainly rely on exploiting external resources and background knowledge to improve the performance and ignore the correlations between entity pairs which are helpful for relation classification. We present the concept of entity pair graph to represent the correlations between entity pairs and propose a novel entity pair graph based neural network (EPGNN) model, relying on graph convolutional network to capture the topological features of an entity pair graph. EPGNN combines sentence semantic features generated by pre-trained BERT model with graph topological features for relation classification. Our proposed model makes full use of a given corpus and forgoes the need of external resources and background knowledge. The experimental results on two widely used dataset: SemEval 2010 Task 8 and ACE 2005, show that our method outperforms the state-of-the-art approaches.

Cite this Paper


BibTeX
@InProceedings{pmlr-v101-zhao19a, title = {Improving Relation Classification by Entity Pair Graph}, author = {Zhao, Yi and Wan, Huaiyu and Gao, Jianwei and Lin, Youfang}, booktitle = {Proceedings of The Eleventh Asian Conference on Machine Learning}, pages = {1156--1171}, year = {2019}, editor = {Lee, Wee Sun and Suzuki, Taiji}, volume = {101}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v101/zhao19a/zhao19a.pdf}, url = {https://proceedings.mlr.press/v101/zhao19a.html}, abstract = {Relation classification is one of the most important tasks in the field of information extraction, and also a key component of systems that require relational understanding of unstructured text. Existing relation classification approaches mainly rely on exploiting external resources and background knowledge to improve the performance and ignore the correlations between entity pairs which are helpful for relation classification. We present the concept of entity pair graph to represent the correlations between entity pairs and propose a novel entity pair graph based neural network (EPGNN) model, relying on graph convolutional network to capture the topological features of an entity pair graph. EPGNN combines sentence semantic features generated by pre-trained BERT model with graph topological features for relation classification. Our proposed model makes full use of a given corpus and forgoes the need of external resources and background knowledge. The experimental results on two widely used dataset: SemEval 2010 Task 8 and ACE 2005, show that our method outperforms the state-of-the-art approaches.} }
Endnote
%0 Conference Paper %T Improving Relation Classification by Entity Pair Graph %A Yi Zhao %A Huaiyu Wan %A Jianwei Gao %A Youfang Lin %B Proceedings of The Eleventh Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Wee Sun Lee %E Taiji Suzuki %F pmlr-v101-zhao19a %I PMLR %P 1156--1171 %U https://proceedings.mlr.press/v101/zhao19a.html %V 101 %X Relation classification is one of the most important tasks in the field of information extraction, and also a key component of systems that require relational understanding of unstructured text. Existing relation classification approaches mainly rely on exploiting external resources and background knowledge to improve the performance and ignore the correlations between entity pairs which are helpful for relation classification. We present the concept of entity pair graph to represent the correlations between entity pairs and propose a novel entity pair graph based neural network (EPGNN) model, relying on graph convolutional network to capture the topological features of an entity pair graph. EPGNN combines sentence semantic features generated by pre-trained BERT model with graph topological features for relation classification. Our proposed model makes full use of a given corpus and forgoes the need of external resources and background knowledge. The experimental results on two widely used dataset: SemEval 2010 Task 8 and ACE 2005, show that our method outperforms the state-of-the-art approaches.
APA
Zhao, Y., Wan, H., Gao, J. & Lin, Y.. (2019). Improving Relation Classification by Entity Pair Graph. Proceedings of The Eleventh Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 101:1156-1171 Available from https://proceedings.mlr.press/v101/zhao19a.html.

Related Material