Somun: entity-centric summarization incorporating pre-trained language models

Text summarization resolves the issue of capturing essential information from a large volume of text data. Existing methods either depend on the end-to-end models or hand-crafted preprocessing steps. In this study, we propose an entity-centric summarization method which extracts named entities and produces a small graph with a dependency parser. To extract entities, we employ well-known pre-trained language models. After generating the graph, we perform the summarization by ranking entities using the harmonic centrality algorithm. Experiments illustrate that we outperform the state-of-the-art unsupervised learning baselines by improving the performance more than 10% for ROUGE-1 and more than 50% for ROUGE-2 scores. Moreover, we achieve comparable results to recent end-to-end models.

Automated summary

This study introduces an entity-centric summarization method that extracts named entities using a dependency parser and generates a small graph, ranking entities using the harmonic centrality algorithm. Experimental results show that it outperforms state-of-the-art unsupervised learning baselines by more than 10% for ROUGE-1 and more than 50% for ROUGE-2 scores, achieving comparable results to recent end-to-end models.