The goal of text summarization is to summarize long text into a short text with main information.To avoid the redundant information brought by the sentence extraction,we propose an extractive summarization model based on a heterogeneous graph network of sub-sentence units,which effectively integrates different levels of language in-formation such as words,entities,and sub-sentential units.Experiments on two large scale benchmark corpora(CNN/DM and NYT)demonstrate that our model yields ground-breaking performance and outperforms previous extractive summarizers.
维普
万方数据