Towards State-of-the-art Baselines for Vietnamese Multi-document Summarization

Text summarization is challenging, but an interesting task of natural language processing. While this task has been widely studied in English, it is still an early stage in Vietnamese. This paper introduces an investigation of extractive summarization methods in Vietnamese. To do that, we implement and compare several well-known summarization methods in three directions: unsupervised, supervised, and deep learning. We validate the performance of the methods on two Vietnamese datasets. According to experimental results, we find two interesting points. Firstly, learning-to-rank methods achieve promising ROUGE-scores in many cases. Particularly, one of them surpasses the state-of-the-art unsupervised learning method. Secondly, formulating the scoring step in the form of learning-to-rank benefits the selection step.