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

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 their effectiveness, most of these models 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 relations. 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.

Authors

• Kun Zhang MBZUAI, Abu Dhabi, UAE, Carnegie Mellon University, Pittsburg, USA
• Le Wu Hefei University of Technology Hefei Comprehensive National Science Center
• Guangyi Lv
• Meng Wang
• Enhong Chen School of Computer Science and Technology, University of Science and Technology of China, Hefei, China State Key Laboratory of Cognitive Intelligence, Hefei, China
• Shulan Ruan

Keywords

No keywords are indexed for this paper.