Hie-BART: Document Summarization with Hierarchical BART

Kazuki Akiyama, Akihiro Tamura, Takashi Ninomiya


Abstract
This paper proposes a new abstractive document summarization model, hierarchical BART (Hie-BART), which captures hierarchical structures of a document (i.e., sentence-word structures) in the BART model. Although the existing BART model has achieved a state-of-the-art performance on document summarization tasks, the model does not have the interactions between sentence-level information and word-level information. In machine translation tasks, the performance of neural machine translation models has been improved by incorporating multi-granularity self-attention (MG-SA), which captures the relationships between words and phrases. Inspired by the previous work, the proposed Hie-BART model incorporates MG-SA into the encoder of the BART model for capturing sentence-word structures. Evaluations on the CNN/Daily Mail dataset show that the proposed Hie-BART model outperforms some strong baselines and improves the performance of a non-hierarchical BART model (+0.23 ROUGE-L).
Anthology ID:
2021.naacl-srw.20
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
159–165
Language:
URL:
https://aclanthology.org/2021.naacl-srw.20
DOI:
10.18653/v1/2021.naacl-srw.20
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-srw.20.pdf