Abstract
In this paper, we introduce a novel BERT-enhanced Relational Sentence Ordering Network (referred to as BRSON) by leveraging BERT for capturing better dependency relationship among sentences to enhance the coherence modeling for the entire paragraph. In particular, we develop a new Relational Pointer Decoder (referred as RPD) by incorporating the relative ordering information into the pointer network with a Deep Relational Module (referred as DRM), which utilizes BERT to exploit the deep semantic connection and relative ordering between sentences. This enables us to strengthen both local and global dependencies among sentences. Extensive evaluations are conducted on six public datasets. The experimental results demonstrate the effectiveness and promise of our BRSON, showing a significant improvement over the state-of-the-art by a wide margin.- Anthology ID:
- 2020.emnlp-main.511
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6310–6320
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.511
- DOI:
- 10.18653/v1/2020.emnlp-main.511
- Cite (ACL):
- Baiyun Cui, Yingming Li, and Zhongfei Zhang. 2020. BERT-enhanced Relational Sentence Ordering Network. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6310–6320, Online. Association for Computational Linguistics.
- Cite (Informal):
- BERT-enhanced Relational Sentence Ordering Network (Cui et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2020.emnlp-main.511.pdf