A BART-based approach with hierarchical strategy for Vietnamese abstractive multi-document summarization

• URL: http://arxiv.org/abs/2606.19591v1
• Date: Wed, 17 Jun 2026 20:46:47 GMT
• Title: A BART-based approach with hierarchical strategy for Vietnamese abstractive multi-document summarization
• Abstract summary: Vietnamese multi-document abstractive summarization was introduced in the International Workshop on Vietnamese Language and Speech Processing (VLSP) 2022.<n>We propose a novel strategy to shorten documents driven by the golden summary, thus ensuring high correlation between stages of the hierarchical approach.<n>Our method achieves a ROUGE2-F1 score of 0.2468 on the VLSP's public test set, and can produce fluent and concise summaries.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this technical report, we focus on solving the challenge of Vietnamese multi-document abstractive summarization, introduced in the International Workshop on Vietnamese Language and Speech Processing (VLSP) 2022. We choose to follow the popular hierarchical approach, i.e. condensing each document followed by aggregation and summarization. We propose a novel yet simple strategy to shorten documents that is driven by the golden summary, thus ensuring high correlation between stages of the hierarchical approach. Our method achieves a ROUGE2-F1 score of 0.2468 on the VLSP's public test set, and can produce fluent and concise summaries. Additionally, we utilize external sources for extra data, which greatly enhances the quantity of data for Vietnamese multi-document summarization. The additional data is made available for the community.

Related papers

• Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization [49.61589046694085]
  We propose a topic-guided reinforcement learning approach to improve content selection in Multi-Document Summarization.<n>We first show that explicitly prompting models with topic labels enhances the informativeness of the generated summaries.
  arXiv  Detail & Related papers  (2025-09-11T21:01:54Z)
• BERT-VBD: Vietnamese Multi-Document Summarization Framework [2.2526595080231857]
  An emerging and promising strategy involves a synergistic fusion of extractive and abstractive summarization methods. This paper presents a novel Vietnamese MDS framework leveraging a two-component pipeline architecture. The proposed framework attains ROUGE-2 scores of 39.6% on the VN-MDS dataset and outperforming the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-09-18T16:56:06Z)
• Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization [48.57273563299046]
  We propose the task of Stepwise Summarization, which aims to generate a new appended summary each time a new document is proposed. The appended summary should not only summarize the newly added content but also be coherent with the previous summary. We show that SSG achieves state-of-the-art performance in terms of both automatic metrics and human evaluations.
  arXiv  Detail & Related papers  (2024-06-08T05:37:26Z)
• Overview of the VLSP 2022 -- Abmusu Shared Task: A Data Challenge for Vietnamese Abstractive Multi-document Summarization [0.6827423171182151]
  The goal of Abmusu shared task is to develop summarization systems that could create abstractive summaries automatically for a set of documents on a topic. We build a human-annotated dataset of 1,839 documents in 600 clusters, collected from Vietnamese news in 8 categories. Models are evaluated and ranked in terms of textttROUGE2-F1 score, the most typical evaluation metric for document summarization problem.
  arXiv  Detail & Related papers  (2023-11-27T04:01:13Z)
• Vietnamese multi-document summary using subgraph selection approach -- VLSP 2022 AbMuSu Shared Task [0.0]
  Document summarization is a task to generate afluent, condensed summary for a document. In this paper, we focus on transforming the extractive MDS problem into subgraph selection. Experiments have been implemented on the Vietnamese dataset published in VLSP Evaluation Campaign 2022.
  arXiv  Detail & Related papers  (2023-06-26T16:34:02Z)
• Generating EDU Extracts for Plan-Guided Summary Re-Ranking [77.7752504102925]
  Two-step approaches, in which summary candidates are generated-then-reranked to return a single summary, can improve ROUGE scores over the standard single-step approach. We design a novel method to generate candidates for re-ranking that addresses these issues. We show large relevance improvements over previously published methods on widely used single document news article corpora.
  arXiv  Detail & Related papers  (2023-05-28T17:22:04Z)
• LBMT team at VLSP2022-Abmusu: Hybrid method with text correlation and generative models for Vietnamese multi-document summarization [1.4716144941085147]
  This paper proposes a method for multi-document summarization based on cluster similarity. After generating summaries by selecting the most important sentences from each cluster, we apply BARTpho and ViT5 to construct the abstractive models.
  arXiv  Detail & Related papers  (2023-04-11T13:15:24Z)
• SgSum: Transforming Multi-document Summarization into Sub-graph Selection [27.40759123902261]
  Most existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary. We propose a novel MDS framework (SgSum) to formulate the MDS task as a sub-graph selection problem. Our model can produce significantly more coherent and informative summaries compared with traditional MDS methods.
  arXiv  Detail & Related papers  (2021-10-25T05:12:10Z)
• PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies [68.8204255655161]
  We propose a reinforcement learning based framework PoBRL for solving multi-document summarization. Our strategy decouples this multi-objective optimization into different subproblems that can be solved individually by reinforcement learning. Our empirical analysis shows state-of-the-art performance on several multi-document datasets.
  arXiv  Detail & Related papers  (2021-05-18T02:55:42Z)
• SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression [61.97200991151141]
  SummPip is an unsupervised method for multi-document summarization. We convert the original documents to a sentence graph, taking both linguistic and deep representation into account. We then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary.
  arXiv  Detail & Related papers  (2020-07-17T13:01:15Z)
• Leveraging Graph to Improve Abstractive Multi-Document Summarization [50.62418656177642]
  We develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries.
  arXiv  Detail & Related papers  (2020-05-20T13:39:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.