Hie-BART: Abstractive Summarization by Hierarchical BART
-
- Akiyama Kazuki
- Graduate School of Science and Engineering, Ehime University
-
- Tamura Akihiro
- Faculty of Science and Engineering, Doshisha University
-
- Ninomiya Takashi
- Graduate School of Science and Engineering, Ehime University
-
- Kajiwara Tomoyuki
- Graduate School of Science and Engineering, Ehime University
Bibliographic Information
- Other Title
-
- Hie-BART: 階層型 BART による生成型要約
Abstract
<p>This paper proposes a new abstractive summarization model for documents, hierarchical BART (Hie-BART), which captures the hierarchical structures of documents (i.e., their sentence-word structures) in the BART model. Although the existing BART model has achieved state-of-the-art performance on document summarization tasks, it does not account for interactions between sentence-level and word-level information. In machine translation tasks, the performance of neural machine translation models can be improved with the incorporation of multi-granularity self-attention (MG-SA), which captures relationships between words and phrases. Inspired by previous work, the proposed Hie-BART model incorporates MG-SA into the encoder of the BART model for capturing sentence-word structures. As for the improvement of summarization performance by the proposed method, the evaluation using the CNN/Daily Mail dataset shows an improvement of 0.1 points on ROUGE-L.</p>
Journal
-
- Journal of Natural Language Processing
-
Journal of Natural Language Processing 29 (3), 835-853, 2022
The Association for Natural Language Processing
- Tweet
Details 詳細情報について
-
- CRID
- 1390856374249881984
-
- ISSN
- 21858314
- 13407619
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- KAKEN
-
- Abstract License Flag
- Disallowed