# LBMT team at VLSP2022-Abmusu: Hybrid method with text correlation and generative models for Vietnamese multi-document summarization

arXiv: https://arxiv.org/abs/2304.05205 · HTML: https://mlsanity.com/paper/2304.05205/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 10 of 10)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [Heterogeneous Graph Neural Networks for Extractive Document Summarization](https://mlsanity.com/paper/2004.12393/) (2020)
- [A Deep Look into Neural Ranking Models for Information Retrieval](https://mlsanity.com/paper/1903.06902/) (2019)
- [Graph-based Neural Multi-Document Summarization](https://mlsanity.com/paper/1706.06681/) (2017)
- [VnCoreNLP: A Vietnamese Natural Language Processing Toolkit](https://mlsanity.com/paper/1801.01331/) (2018)
- [ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation](https://mlsanity.com/paper/2205.06457/) (2022)
- [BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese](https://mlsanity.com/paper/2109.09701/) (2021)
- [Transformer-based Approaches for Legal Text Processing](https://mlsanity.com/paper/2202.06397/) (2022)

## Abstract (arXiv)

Multi-document summarization is challenging because the summaries should not only describe the most important information from all documents but also provide a coherent interpretation of the documents. This paper proposes a method for multi-document summarization based on cluster similarity. In the extractive method we use hybrid model based on a modified version of the PageRank algorithm and a text correlation considerations mechanism. After generating summaries by selecting the most important sentences from each cluster, we apply BARTpho and ViT5 to construct the abstractive models. Both extractive and abstractive approaches were considered in this study. The proposed method achieves competitive results in VLSP 2022 competition.