Papers › Hie-BART: Document Summarization with Hierarchical BART

Hie-BART: Document Summarization with Hierarchical BART

1 Jun 2021NAACL 2021 4archive 2025-07-28

Kazuki Akiyama, Akihiro Tamura, Takashi Ninomiya

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).

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Document SummarizationMachine TranslationSentenceTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Summarization CNN / Daily Mail Hie-BART ROUGE-1 44.35 #7 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Hie-BART ROUGE-2 21.37 #7 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail Hie-BART ROUGE-L 41.05 #7 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionBARTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections