Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching

Authors

  • Kun Zhang School of Computer Science and Information Engineering, Hefei University of Technology
  • Le Wu School of Computer Science and Information Engineering, Hefei University of Technology Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
  • Guangyi Lv Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China
  • Meng Wang School of Computer Science and Information Engineering, Hefei University of Technology Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
  • Enhong Chen Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China
  • Shulan Ruan Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China

Keywords:

Text Classification & Sentiment Analysis

Abstract

Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially BERT. Despite the effectiveness of these models, most of them treat output labels as meaningless one-hot vectors, underestimating the semantic information and guidance of relations that these labels reveal, especially for tasks with a small number of labels. To address this problem, we propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. Specifically, we first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task for guiding R2-Net to consider more about labels. Meanwhile, a triplet loss is employed to distinguish the intra-class and inter-class relations in a finer granularity. Empirical experiments on two sentence semantic matching tasks demonstrate the superiority of our proposed model. As a byproduct, we have released the codes to facilitate other researches.

Downloads

Published

2021-05-18

How to Cite

Zhang, K., Wu, L., Lv, G., Wang, M., Chen, E., & Ruan, S. (2021). Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 14411-14419. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17694

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing III