Relation Extraction Using Supervision from Topic Knowledge of Relation Labels

Explicitly exploring the semantics of a relation is significant for high-accuracy relation extraction, which is, however, not fully studied in previous work. In this paper, we mine the topic knowledge of a relation to explicitly represent the semantics of this relation, and model relation extraction as a matching problem. That is, the matching score between a sentence and a candidate relation is predicted for an entity pair. To this end, we propose a deep matching network to precisely model the semantic similarity between a sentence-relation pair. Besides, the topic knowledge also allows us to derive the importance information of samples as well as two knowledge-guided negative sampling strategies in the training process. We conduct extensive experiments to evaluate the proposed framework and observe improvements in AUC of 11.5% and max F1 of 5.4% over the baselines with state-ofthe-art performance.

[1]  Chang Wang,et al.  Relation Extraction with Relation Topics , 2011, EMNLP.

[2]  Jun Zhao,et al.  Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks , 2015, EMNLP.

[3]  Enrique Alfonseca,et al.  Pattern Learning for Relation Extraction with a Hierarchical Topic Model , 2012, ACL.

[4]  Anita Alicante,et al.  Barrier Features for Classification of Semantic Relations , 2011, RANLP.

[5]  Sameer Singh,et al.  Injecting Logical Background Knowledge into Embeddings for Relation Extraction , 2015, NAACL.

[6]  Baogang Wei,et al.  Dependency-based Siamese long short-term memory network for learning sentence representations , 2018, PloS one.

[7]  Li Zhao,et al.  Reinforcement Learning for Relation Classification From Noisy Data , 2018, AAAI.

[8]  Chengqi Zhang,et al.  Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling , 2018, ICLR.

[9]  Andrew McCallum,et al.  Modeling Relations and Their Mentions without Labeled Text , 2010, ECML/PKDD.

[10]  Alan Wee-Chung Liew,et al.  Multi-label classification via label correlation and first order feature dependance in a data stream , 2019, Pattern Recognit..

[11]  Daniel Jurafsky,et al.  Distant supervision for relation extraction without labeled data , 2009, ACL.

[12]  Jian Su,et al.  Exploring Various Knowledge in Relation Extraction , 2005, ACL.

[13]  Luke S. Zettlemoyer,et al.  Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations , 2011, ACL.

[14]  David Bamman,et al.  Adversarial Training for Relation Extraction , 2017, EMNLP.

[15]  Jun Zhao,et al.  Relation Classification via Convolutional Deep Neural Network , 2014, COLING.

[16]  Peng Li,et al.  Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks , 2016, COLING.

[17]  Zhiyuan Liu,et al.  Neural Relation Extraction with Selective Attention over Instances , 2016, ACL.

[18]  Razvan C. Bunescu,et al.  A Shortest Path Dependency Kernel for Relation Extraction , 2005, HLT.

[19]  Jun Zhao,et al.  Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions , 2017, AAAI.

[20]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[21]  Peng Zhou,et al.  Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme , 2017, ACL.

[22]  Matt J. Kusner,et al.  From Word Embeddings To Document Distances , 2015, ICML.