BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation

Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, Jana Diesner


Abstract
In this paper, we focus on the problem of citing sentence generation, which entails generating a short text to capture the salient information in a cited paper and the connection between the citing and cited paper. We present BACO, a BAckground knowledge- and COntent-based framework for citing sentence generation, which considers two types of information: (1) background knowledge by leveraging structural information from a citation network; and (2) content, which represents in-depth information about what to cite and why to cite. First, a citation network is encoded to provide background knowledge. Second, we apply salience estimation to identify what to cite by estimating the importance of sentences in the cited paper. During the decoding stage, both types of information are combined to facilitate the text generation, and then we conduct a joint training for the generator and citation function classification to make the model aware of why to cite. Our experimental results show that our framework outperforms comparative baselines.
Anthology ID:
2021.acl-long.116
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1466–1478
Language:
URL:
https://aclanthology.org/2021.acl-long.116
DOI:
10.18653/v1/2021.acl-long.116
Bibkey:
Cite (ACL):
Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, and Jana Diesner. 2021. BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1466–1478, Online. Association for Computational Linguistics.
Cite (Informal):
BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation (Ge et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.116.pdf
Optional supplementary material:
 2021.acl-long.116.OptionalSupplementaryMaterial.zip
Video:
 https://aclanthology.org/2021.acl-long.116.mp4