Abstract
This paper surveys several recent abstract summarization methods: T5, Pegasus, and ProphetNet. We implement the systems in two languages: English and Indonesian languages. We investigate the impact of pre-training models (one T5, three Pegasuses, three ProphetNets) on several Wikipedia datasets in English and Indonesian language and compare the results to the Wikipedia systems' summaries. The T5-Large, the Pegasus-XSum, and the ProphetNet-CNNDM provide the best summarization. The most significant factors that influence ROUGE performance are coverage, density, and compression. The higher the scores, the better the summary. Other factors that influence the ROUGE scores are the pre-training goal, the dataset's characteristics, the dataset used for testing the pre-trained model, and the cross-lingual function. Several suggestions to improve this paper's limitation are: 1) assure that the dataset used for the pre-training model must sufficiently large, contains adequate instances for handling cross-lingual purpose; 2) Advanced process (finetuning) shall be reasonable. We recommend using the large dataset consists of comprehensive coverage of topics from many languages before implementing advanced processes such as the train-infer-train procedure to the zero-shot translation in the training stage of the pre-training model.
Abstract (translated)
URL
https://arxiv.org/abs/2105.00824
