Neural Sentence Ordering Based on Constraint Graphs


  • Yutao Zhu Université de Montréal
  • Kun Zhou Renmin University of China
  • Jian-Yun Nie Université de Montréal
  • Shengchao Liu Mila Université de Montréal
  • Zhicheng Dou Remin University, China


Discourse, Pragmatics & Argument Mining


Sentence ordering aims at arranging a list of sentences in the correct order. Based on the observation that sentence order at different distances may rely on different types of information, we devise a new approach based on multi-granular orders between sentences. These orders form multiple constraint graphs, which are then encoded by Graph Isomorphism Networks and fused into sentence representations. Finally, sentence order is determined using the order-enhanced sentence representations. Our experiments on five benchmark datasets show that our method outperforms all existing baselines significantly, achieving a new state-of-the-art performance. The results demonstrate the advantage of considering multiple types of order information and using graph neural networks to integrate sentence content and order information for the task. Our code is available at




How to Cite

Zhu, Y., Zhou, K., Nie, J.-Y., Liu, S., & Dou, Z. (2021). Neural Sentence Ordering Based on Constraint Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 14656-14664. Retrieved from



AAAI Technical Track on Speech and Natural Language Processing III