This paper reports the overview of the VLSP 2022 - Vietnamese abstractive multi-document summarization (Abmusu) shared task for Vietnamese News. This task is hosted at the 9th annual workshop on Vietnamese Language and Speech Processing (VLSP 2022). 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. The model input is multiple news documents on the same topic, and the corresponding output is a related abstractive summary. In the scope of Abmusu shared task, we only focus on Vietnamese news summarization and build a human-annotated dataset of 1,839 documents in 600 clusters, collected from Vietnamese news in 8 categories. Participated models are evaluated and ranked in terms of \texttt{ROUGE2-F1} score, the most typical evaluation metric for document summarization problem.
@article{arxiv.2311.15525,
title = {Overview of the VLSP 2022 -- Abmusu Shared Task: A Data Challenge for Vietnamese Abstractive Multi-document Summarization},
author = {Mai-Vu Tran and Hoang-Quynh Le and Duy-Cat Can and Quoc-An Nguyen},
journal= {arXiv preprint arXiv:2311.15525},
year = {2023}
}