Automatic text summarization based on extractive-abstractive method

Abstract

The choice of this study has a significant impact on daily life. In various fields such as journalism, academia, business, and more, large amounts of text need to be processed quickly and efficiently. Text summarization is a technique used to generate a precise and shortened summary of spacious texts. The generated summary sustains overall meaning without losing any information and focuses on those parts that contain useful information. The goal is to develop a model that converts lengthy articles into concise versions. The task to be solved is to select an effective procedure to develop the model. Although the present text summarization models give us good results in many recognized datasets such as cnn/daily- mail, newsroom, etc. All the problems can not be resolved by these models. In this paper, a new text summarization method has been proposed: combining the Extractive and Abstractive Text Summarization technique. In the extractive-based method, the model generates a summary using Sentence Ranking Algorithm and passes this generated summary through an abstractive method. When using the sentence ranking algorithm, after rearranging the sentences, the relationship between one sentence and another sentence is destroyed. To overcome this situation, Pronoun to Noun conversion has been proposed with the new system. After generating the extractive summary, the generated summary is passed through the abstractive method. The proposed abstractive model consists of three pre-trained models: google/pegusus-xsum, face-book/bart-large-cnn model, and Yale-LILY/brio-cnndm-uncased, which generates a final summary depending on the maximum final score. The following results were obtained: experimental results on CNN/daily-mail dataset show that the proposed model obtained scores of ROUGE-1, ROUGE-2 and ROUGE-L are respectively 42.67 %, 19.35 %, and 39.57 %. Then, the result has been compared with three state-of-the-art methods: JEANS, DEATS and PGAN-ATSMT. The results outperform state-of-the-art models. Experimental results also show that the proposed model is qualitatively readable and can generate abstract summaries. Conclusion: In terms of ROUGE score, the model outperforms some art-of-the-state models for ROUGE-1 and ROUGE-L, but doesn’t achieve good result in ROUGE-2.