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.

本文介绍了一种基于聚类相似性的多文档综述方法，使用基于修改版 PageRank 算法和文本相关性考虑机制的混合模型的抽取方法，在每个聚类中选择最重要的句子生成摘要，并应用 BARTpho 和 ViT5 构建了缩写模型，结果表明该方法在 VLSP 2022 竞赛中取得了竞争力的成果。

VLSP2022-Abmusu 比赛中 LBMT 队伍使用文本相关性和生成模型的混合方法进行越南多文档摘要

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

In this paper, we explore the construction of natural language explanations
for news claims, with the goal of assisting fact-checking and news evaluation
applications. We experiment with two methods: (1) an extractive method based on
Biased TextRank -- a resource-effective unsupervised graph-based algorithm for
content extraction; and (2) an abstractive method based on the GPT-2 language
model. We perform comparative evaluations on two misinformation datasets in the
political and health news domains, and find that the extractive method shows
the most promise.

本文探讨了构建自然语言解释来辅助事实核查和新闻评估应用的目标，在两个误解数据集中，基于 Biased TextRank 的提取方法表现最有潜力。